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

    Neuronpedia

    INDEX
    Explanations

    join game

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _boxes
    -0.07
     声
    -0.06
     staff
    -0.06
    ו
    -0.06
    �
    -0.06
    Limits
    -0.06
    Nu
    -0.06
    語
    -0.06
    сторія
    -0.06
    -third
    -0.06
    POSITIVE LOGITS
    _attribute
    0.07
     Dealer
    0.07
     toler
    0.06
    ава
    0.06
     shortfall
    0.06
     Admin
    0.06
    .Helper
    0.06
    IMUM
    0.06
     серпня
    0.06
    átor
    0.06
    Act Density 0.008%

    No Known Activations