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

    Neuronpedia

    INDEX
    Explanations

    ad

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     превыш
    -0.07
     Formation
    -0.07
     것은
    -0.06
     서비스
    -0.06
    .Note
    -0.06
     Πρω
    -0.06
     Sailor
    -0.06
     นาย
    -0.06
    руш
    -0.06
     nghiêm
    -0.06
    POSITIVE LOGITS
     genitals
    0.06
     genital
    0.06
     config
    0.06
     varlık
    0.06
    endent
    0.06
    $status
    0.06
    ano
    0.06
     DD
    0.06
               ↵
    0.06
    ANO
    0.06
    Act Density 0.006%

    No Known Activations