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

    Neuronpedia

    INDEX
    Explanations

    lines, intersections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ヤモンド
    1.34
    <unused232>
    1.21
    <unused1863>
    1.21
    剐
    1.20
    埝
    1.20
    lockSeconds
    1.19
    DCTask
    1.18
    lical
    1.16
    PERATURE
    1.16
    <unused1722>
    1.16
    POSITIVE LOGITS
    sh
    1.15
    sides
    1.02
    र
    0.95
    w
    0.94
    much
    0.93
    s
    0.93
    law
    0.91
    ючи
    0.91
    Law
    0.89
    were
    0.89
    Act Density 0.000%

    No Known Activations