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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     установки
    -0.07
    arker
    -0.07
     Kabul
    -0.07
    minute
    -0.07
     yapıldı
    -0.07
    Align
    -0.07
     rowNum
    -0.06
    arsity
    -0.06
    phet
    -0.06
    )‏
    -0.06
    POSITIVE LOGITS
     рекоменда
    0.07
    \Auth
    0.07
    	ad
    0.07
     Lie
    0.06
     Comb
    0.06
     credit
    0.06
     latitude
    0.06
     Deleted
    0.06
     promotion
    0.06
     Crusher
    0.06
    Act Density 0.012%

    No Known Activations