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

    Neuronpedia

    INDEX
    Explanations

    internet text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    urator
    -0.07
    intelligence
    -0.07
     Анд
    -0.06
     отверсти
    -0.06
     zkou
    -0.06
     Brad
    -0.06
    -Muslim
    -0.06
    背
    -0.06
     भगव
    -0.06
    _Bl
    -0.06
    POSITIVE LOGITS
     기
    0.07
    .object
    0.07
    ADATA
    0.07
    _↵
    0.06
     hindsight
    0.06
     potentially
    0.06
     Valid
    0.06
    ्ग
    0.06
    _centers
    0.06
    pai
    0.06
    Act Density 0.000%

    No Known Activations