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

    Neuronpedia

    INDEX
    Explanations

    roleplay

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    พวก
    -0.07
    -clock
    -0.07
     Fiji
    -0.07
    رانه
    -0.07
    BM
    -0.07
    elect
    -0.06
    еса
    -0.06
    SID
    -0.06
    アニメ
    -0.06
    rhs
    -0.06
    POSITIVE LOGITS
    %
↵
    0.06
    aunch
    0.06
    lexible
    0.06
    (bot
    0.06
    êt
    0.06
    _ACTIVITY
    0.06
    #\
    0.06
     insider
    0.06
    (sb
    0.06
    Deck
    0.06
    Act Density 0.034%

    No Known Activations