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

    Neuronpedia

    INDEX
    Explanations

    GPI, genuine threat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    or
    0.54
    id
    0.51
    Cz
    0.49
    CZ
    0.48
    licht
    0.47
    by
    0.46
    ON
    0.46
    setzen
    0.46
    čila
    0.46
    list
    0.45
    POSITIVE LOGITS
     strategic
    0.60
     driver
    0.49
    ী
    0.49
     director
    0.48
    ের
    0.48
    적으로
    0.48
     collective
    0.47
     definitive
    0.46
     linker
    0.46
    лаве
    0.46
    Act Density 0.000%

    No Known Activations