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

    Neuronpedia

    INDEX
    Explanations

    bail bonds, jailbreak, rainn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝐧
    1.12
     integrable
    0.96
    ّا
    0.93
     cadena
    0.92
     концерт
    0.91
    ّه
    0.91
    ాయ
    0.90
     concert
    0.89
     dst
    0.89
     maî
    0.88
    POSITIVE LOGITS
    kho
    1.11
    brushes
    1.06
    lust
    1.05
    borhood
    1.04
    brush
    1.04
    kde
    0.99
    staking
    0.98
    eenth
    0.98
    natal
    0.97
    ボリー
    0.97
    Act Density 0.193%

    No Known Activations