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

    Neuronpedia

    INDEX
    Explanations

    Digits 3 or 4

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .dataGridViewTextBoxColumn
    -0.07
    ，当
    -0.07
    102
    -0.07
    200
    -0.07
    lean
    -0.07
    252
    -0.07
     заболевания
    -0.06
    ueil
    -0.06
    新的
    -0.06
    נ
    -0.06
    POSITIVE LOGITS
    5
    0.11
    6
    0.09
    4
    0.09
    7
    0.09
    3
    0.09
    8
    0.08
    g
    0.08
    or
    0.06
     GH
    0.06
     disciples
    0.06
    Act Density 0.125%

    No Known Activations