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

    Neuronpedia

    INDEX
    Explanations

    graph theory variables m, n

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _CHO
    -0.10
    _choices
    -0.09
     ณ
    -0.08
    Choices
    -0.08
     вечером
    -0.08
    Issuer
    -0.08
     Bezos
    -0.08
     семьи
    -0.08
     interview
    -0.08
    午後
    -0.08
    POSITIVE LOGITS
    sie
    0.10
     Width
    0.09
     width
    0.09
     grids
    0.09
     latt
    0.09
    (width
    0.09
     widths
    0.09
    尺寸
    0.09
    -width
    0.08
    .width
    0.08
    Act Density 0.010%

    No Known Activations