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

    Neuronpedia

    INDEX
    Explanations

    kittens

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jefus
    -0.92
     Efq
    -0.91
     Мексичка
    -0.88
    CppMethod
    -0.88
     itſelf
    -0.87
    ^(@)
    -0.86
     myſelf
    -0.85
     photolibrary
    -0.84
     الرياضيه
    -0.82
     purpoſe
    -0.82
    POSITIVE LOGITS
     
    0.67
    .
    0.65
     et
    0.56
    a
    0.56
    '
    0.54
    hip
    0.52
    ,
    0.50
     (
    0.50
    ’
    0.50
    :
    0.49
    Act Density 1.291%

    No Known Activations