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

    Neuronpedia

    INDEX
    Explanations

    class

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .
    -0.87
    :
    -0.73
     
    -0.71
     tinggi
    -0.64
    ,
    -0.64
     higher
    -0.60
    ;
    -0.59
    !
    -0.58
     (
    -0.57
     high
    -0.57
    POSITIVE LOGITS
    تقاوى
    1.23
    ^(@)
    1.07
    脚注の使い方
    1.02
    OGND
    1.01
    FunctionFlags
    0.97
    ſelves
    0.97
    /−
    0.96
     itſelf
    0.96
    setVerticalGroup
    0.95
    ſelf
    0.93
    Act Density 0.033%

    No Known Activations