Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    terms related to directed graphical models and their structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Tokens followed by a $ or relating to graphs

    np_acts-logits-general · gemini-2.0-flash

    master slave relationship implies subset

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCompany
    -0.43
    VYMaps
    -0.41
    ="@+
    -0.41
    AndEndTag
    -0.39
     invokingState
    -0.38
     opérateurs
    -0.36
     ſer
    -0.36
    Altern
    -0.34
     ſol
    -0.33
     surla
    -0.33
    POSITIVE LOGITS
     subordinate
    0.49
    tvguidetime
    0.43
    Personendaten
    0.43
    Identyfik
    0.43
     subordination
    0.42
    RotationOrder
    0.41
     subordinates
    0.41
    bootstrapcdn
    0.40
    السكان
    0.40
     daripada
    0.40
    Act Density 0.927%

    No Known Activations