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

    Neuronpedia

    INDEX
    Explanations

    .title

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _eval
    -0.08
    懈
    -0.07
    ܆
    -0.07
    基�
    -0.07
    捐助
    -0.07
    _Module
    -0.07
     subtly
    -0.07
    .Assert
    -0.07
    Dataset
    -0.06
    (ctx
    -0.06
    POSITIVE LOGITS
    ificação
    0.07
     ['/
    0.07
    **,
    0.07
     thinkers
    0.07
     shorten
    0.07
     stringValue
    0.06
    -war
    0.06
     '**
    0.06
     plataforma
    0.06
     ripple
    0.06
    Act Density 0.003%

    No Known Activations