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

    Neuronpedia

    INDEX
    Explanations

    1 or 2

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .accel
    -0.08
    M
    -0.08
    el
    -0.07
    𬭁
    -0.07
    v
    -0.07
    վ
    -0.07
    row
    -0.07
     виде
    -0.07
    体温
    -0.06
    (groups
    -0.06
    POSITIVE LOGITS
     vectors
    0.08
    ']
↵
↵
    0.07
    )):↵
    0.07
    妻子
    0.07
    _txt
    0.07
    )):
↵
    0.07
     "@
    0.06
     Chest
    0.06
    *
↵
    0.06
    なら
    0.06
    Act Density 0.199%

    No Known Activations