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

    Neuronpedia

    INDEX
    Explanations

    caller

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    awtextra
    -1.04
     myſelf
    -0.86
     becauſe
    -0.83
     Theſe
    -0.82
     itſelf
    -0.81
     raiſ
    -0.81
    InputBorder
    -0.79
     Beſ
    -0.78
     ſche
    -0.77
    RenderAtEndOf
    -0.76
    POSITIVE LOGITS
    ,
    0.58
     in
    0.55
     on
    0.54
     to
    0.53
     or
    0.53
     M
    0.53
    .
    0.52
     F
    0.48
     and
    0.47
     from
    0.44
    Act Density 0.108%

    No Known Activations