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

    Neuronpedia

    INDEX
    Explanations

    references to business entities and their offerings

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

    company or firm descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    turnstile
    -0.54
    ollectionView
    -0.53
    yorlar
    -0.53
     Họ
    -0.53
    dyž
    -0.52
    ThroughAttribute
    -0.51
     eſſ
    -0.50
    istoitu
    -0.49
    ſelves
    -0.49
     Egipto
    -0.49
    POSITIVE LOGITS
     myself
    0.36
    MathML
    0.32
    instancetype
    0.31
    WriteTagHelper
    0.30
     Mig
    0.30
     responsibly
    0.30
    我自己
    0.30
     Jay
    0.29
     Myself
    0.29
     goal
    0.29
    Act Density 0.027%

    No Known Activations