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

    Neuronpedia

    INDEX
    Explanations

    puzzle

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ﺪ
    -0.07
    휴
    -0.06
     thủy
    -0.06
    kah
    -0.06
    üst
    -0.06
    >[↵
    -0.06
    τεί
    -0.06
    人的
    -0.06
     theology
    -0.06
     faut
    -0.06
    POSITIVE LOGITS
     acknowledgment
    0.07
     Adaptive
    0.06
     Stamford
    0.06
    (operator
    0.06
    AMP
    0.06
     считается
    0.06
     μέχρι
    0.06
    device
    0.06
     επίσης
    0.06
     Ston
    0.06
    Act Density 0.065%

    No Known Activations