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

    Neuronpedia

    INDEX
    Explanations

    o

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     درخواست
    -0.07
    standing
    -0.07
     Sit
    -0.07
     ct
    -0.06
     шляхом
    -0.06
     колич
    -0.06
     Harmony
    -0.06
    CursorPosition
    -0.06
     deer
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    _pres
    0.07
    -containing
    0.06
    (rules
    0.06
    는다
    0.06
     речі
    0.06
     bum
    0.06
    ексу
    0.06
    idden
    0.06
    assist
    0.06
     Vuex
    0.05
    Act Density 0.003%

    No Known Activations