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

    Neuronpedia

    INDEX
    Explanations

    provides

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Executive
    -0.07
     mods
    -0.07
    Culture
    -0.07
    址
    -0.07
    ادة
    -0.06
    irl
    -0.06
     Colin
    -0.06
    .writeln
    -0.06
    ,type
    -0.06
     Telegraph
    -0.06
    POSITIVE LOGITS
     itinerary
    0.06
     compass
    0.06
    बर
    0.06
    рост
    0.06
     insurgents
    0.06
     EditText
    0.06
    CED
    0.06
     Liebe
    0.06
    _GT
    0.06
    KT
    0.06
    Act Density 0.595%

    No Known Activations