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

    Neuronpedia

    INDEX
    Explanations

    paper

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _lists
    -0.08
    WAR
    -0.07
    film
    -0.07
    .getIn
    -0.07
     Dön
    -0.06
    vědom
    -0.06
    }.↵
    -0.06
    σ
    -0.06
    製作
    -0.06
    ,function
    -0.06
    POSITIVE LOGITS
     color
    0.07
     called
    0.06
     UTIL
    0.06
     istem
    0.06
     princip
    0.06
    .salary
    0.06
     jou
    0.06
    総
    0.06
    ERRY
    0.06
    าษ
    0.06
    Act Density 0.000%

    No Known Activations