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

    Neuronpedia

    INDEX
    Explanations

    elements you requested

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    0.67
    e
    0.60
    R
    0.59
    er
    0.59
    ER
    0.59
    E
    0.54
    i
    0.53
    A
    0.53
    F
    0.49
    L
    0.48
    POSITIVE LOGITS
    PerTrial
    0.63
    <unused294>
    0.62
    .$.
    0.60
     безопасности
    0.58
     управления
    0.56
     рассказывает
    0.56
     brochures
    0.55
    :&
    0.55
    <unused88>
    0.55
    ):["
    0.55
    Act Density 1.186%

    No Known Activations