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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    NG
    -0.07
     LEVEL
    -0.06
     Sink
    -0.06
     سف
    -0.06
     ẩm
    -0.06
    TRACT
    -0.06
    TemplateName
    -0.06
     yapan
    -0.06
     underneath
    -0.06
    (C
    -0.06
    POSITIVE LOGITS
    outil
    0.07
    raph
    0.07
    .cli
    0.07
    bool
    0.07
    .pkl
    0.07
    }-{
    0.06
     appalling
    0.06
    	in
    0.06
    _done
    0.06
    ализ
    0.06
    Act Density 0.003%

    No Known Activations