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

    Neuronpedia

    INDEX
    Explanations

    goat nibbled

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     );//
    0.79
     плодо
    0.70
    getStartState
    0.66
     ακ
    0.66
    cientes
    0.66
     коопера
    0.65
    0.64
    硌
    0.64
     nejsou
    0.63
     επ
    0.63
    POSITIVE LOGITS
    M
    1.05
    H
    1.02
    I
    0.97
    G
    0.96
    R
    0.93
    1
    0.91
    2
    0.91
    Z
    0.85
    Г
    0.82
    D
    0.82
    Act Density 0.001%

    No Known Activations