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

    Neuronpedia

    INDEX
    Explanations

    settings paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Einwill
    0.50
    祹
    0.50
     Activision
    0.49
    勰
    0.49
    akaran
    0.49
    <unused1808>
    0.48
    ЕМ
    0.48
     Marissa
    0.48
     nigris
    0.47
     протя
    0.47
    POSITIVE LOGITS
    fn
    0.55
    vertical
    0.50
    \
    0.48
    fuel
    0.47
    ↵
    0.47
    lat
    0.47
    scale
    0.47
    high
    0.46
    '
    0.46
    0.46
    Act Density 0.000%

    No Known Activations