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

    Neuronpedia

    INDEX
    Explanations

    3

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    869
    -0.07
     Singh
    -0.07
     Dom
    -0.06
     DL
    -0.06
     çevir
    -0.06
     denominator
    -0.06
     Cycling
    -0.06
     справж
    -0.06
    ermen
    -0.06
     Putin
    -0.06
    POSITIVE LOGITS
     tasting
    0.06
     helf
    0.06
    RTOS
    0.06
     retract
    0.06
     puedes
    0.06
     bad
    0.06
     dividends
    0.06
    depending
    0.06
    ])-
    0.06
     무
    0.06
    Act Density 0.009%

    No Known Activations