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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     리스트
    -0.06
     beliefs
    -0.06
     Bew
    -0.06
     快
    -0.06
     percentages
    -0.06
     Experimental
    -0.06
     surveys
    -0.06
    including
    -0.06
     Бог
    -0.06
    研究
    -0.06
    POSITIVE LOGITS
    _ENDIAN
    0.07
    _tD
    0.07
    _DAC
    0.07
     становить
    0.07
    _EQUALS
    0.07
    nginx
    0.06
    OfDay
    0.06
    ecko
    0.06
     mandates
    0.06
    kar
    0.06
    Act Density 0.001%

    No Known Activations