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

    Neuronpedia

    INDEX
    Explanations

    opinions and arguments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wildcard
    -0.06
    icons
    -0.06
    半
    -0.06
    ०
    -0.06
     크
    -0.06
     none
    -0.06
    掉
    -0.06
     ARRAY
    -0.06
     inviting
    -0.06
     Adapter
    -0.05
    POSITIVE LOGITS
    ктів
    0.06
    cháze
    0.06
    eted
    0.06
    _WM
    0.06
    �
    0.06
    gmt
    0.06
     بدن
    0.06
    restore
    0.06
    _scheme
    0.06
     mindfulness
    0.06
    Act Density 0.112%

    No Known Activations