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

    Neuronpedia

    INDEX
    Explanations

    rolling dice sums

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     housekeeper
    0.43
    endedor
    0.40
    estabelecimento
    0.39
    getAsJsonObject
    0.38
     बटे
    0.37
     xấu
    0.37
     kasutada
    0.37
     mascotas
    0.37
    andum
    0.37
     использования
    0.37
    POSITIVE LOGITS
     Lorentz
    0.40
     Challenge
    0.39
     Multi
    0.39
     Ore
    0.38
     Rees
    0.38
     Gore
    0.38
     Booth
    0.38
    <0xE9>
    0.37
     Grant
    0.37
     Noise
    0.37
    Act Density 0.000%

    No Known Activations