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

    Neuronpedia

    INDEX
    Explanations

    guilty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    xxx
    -0.07
     comer
    -0.07
     puff
    -0.07
     Malta
    -0.06
    erb
    -0.06
    さい
    -0.06
    ानम
    -0.06
    Buscar
    -0.06
     garbage
    -0.06
    ta
    -0.06
    POSITIVE LOGITS
    Passwords
    0.06
     DateTimeOffset
    0.06
    etik
    0.06
     Classical
    0.06
     TODAY
    0.06
    pectives
    0.06
     church
    0.06
    ernetes
    0.06
     자동
    0.06
     senate
    0.06
    Act Density 0.006%

    No Known Activations