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

    Neuronpedia

    INDEX
    Explanations

    Drake

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    เวอร
    -0.07
     Capture
    -0.07
     raping
    -0.07
    _Rel
    -0.07
    หลาย
    -0.07
    _alive
    -0.06
    _KEEP
    -0.06
    ρος
    -0.06
     tym
    -0.06
    ンジ
    -0.06
    POSITIVE LOGITS
    İK
    0.07
    arios
    0.06
    ствен
    0.06
    TRY
    0.06
     aba
    0.06
     aspir
    0.06
    senha
    0.06
    İN
    0.06
     resp
    0.06
     sweater
    0.06
    Act Density 0.004%

    No Known Activations