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

    Neuronpedia

    INDEX
    Explanations

    HTML tags and their attributes

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

    navigation links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſch
    -0.88
     ſche
    -0.88
     ſta
    -0.84
     Verſ
    -0.82
     AssemblyCulture
    -0.81
     queſta
    -0.80
     ddelwed
    -0.80
     purpoſe
    -0.79
     myſelf
    -0.79
     ſont
    -0.78
    POSITIVE LOGITS
    a
    0.40
    ia
    0.39
    o
    0.36
    i
    0.35
    s
    0.34
    A
    0.33
    ob
    0.33
    O
    0.33
    no
    0.32
    ea
    0.32
    Act Density 0.018%

    No Known Activations