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

    Neuronpedia

    INDEX
    Explanations

    foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ifest
    -0.08
     tác
    -0.07
    prisingly
    -0.07
     attract
    -0.07
    mitted
    -0.07
    稻
    -0.07
    <i
    -0.07
    莸
    -0.07
    adm
    -0.06
     chilled
    -0.06
    POSITIVE LOGITS
    _RANGE
    0.07
     storyline
    0.07
    MATRIX
    0.07
    triangle
    0.07
    높
    0.07
     enlargement
    0.06
    -not
    0.06
    ɚ
    0.06
    ϱ
    0.06
     saldırı
    0.06
    Act Density 0.001%

    No Known Activations