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

    Neuronpedia

    INDEX
    Explanations

    content related to discussions or opinions about strategies and decisions

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

    Follows a question or statement

    np_acts-logits-general · gemini-2.0-flash

    basically, essentially, what

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.65
    tagHelperRunner
    -0.60
     विश्वसनीयता
    -0.58
    endwhile
    -0.58
     betweenstory
    -0.57
    CloseOperation
    -0.56
    SharedModule
    -0.56
    كذا
    -0.54
    ModelSerializer
    -0.54
    LookAnd
    -0.54
    POSITIVE LOGITS
     what
    1.28
    what
    0.99
    What
    0.92
     essentially
    0.89
     What
    0.86
     basically
    0.86
    Basically
    0.82
     Essentially
    0.81
    essentially
    0.80
     Basically
    0.80
    Act Density 0.424%

    No Known Activations