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

    Neuronpedia

    INDEX
    Explanations

    ensure every child

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ্যোগ
    1.06
    ්
    1.05
     conmigo
    1.04
     önceki
    1.03
    wagen
    1.03
    w
    1.02
     brasile
    1.01
     concili
    1.00
     タイプ
    0.99
     hechos
    0.99
    POSITIVE LOGITS
     naught
    1.13
     shortcut
    1.10
    visits
    1.08
    nobody
    1.07
    ী
    1.07
    anyone
    1.07
    д
    1.06
    Everyone
    1.06
    로
    1.04
    ју
    1.04
    Act Density 0.000%

    No Known Activations