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

    Neuronpedia

    INDEX
    Explanations

    warp drive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -
    1.12
    지
    0.95
    ę
    0.86
    ۰
    0.82
     stoked
    0.75
    ०
    0.73
    কার
    0.72
    들이
    0.72
    ção
    0.71
    łym
    0.71
    POSITIVE LOGITS
     filial
    0.72
    Ꮕ
    0.70
     avoc
    0.69
    }.
    0.68
     ebenso
    0.68
     leeftijd
    0.67
     эпоху
    0.67
     изображения
    0.66
     использовании
    0.66
    ोत
    0.64
    Act Density 0.001%

    No Known Activations