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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Protest
    -0.07
     ([]
    -0.07
    distribution
    -0.07
    경제
    -0.06
    ceptions
    -0.06
    housing
    -0.06
     varlık
    -0.06
     chromosomes
    -0.06
    ícul
    -0.06
     synthesized
    -0.06
    POSITIVE LOGITS
    א
    0.07
     Sole
    0.07
    /Login
    0.07
    支援
    0.06
    brıs
    0.06
     specialists
    0.06
    -title
    0.06
     ін
    0.06
    940
    0.06
     موب
    0.06
    Act Density 0.020%

    No Known Activations