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

    Neuronpedia

    INDEX
    Explanations

    Code/data snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     brand
    -0.08
    ら
    -0.06
    центра
    -0.06
    打开
    -0.06
     Damn
    -0.06
     rival
    -0.06
    으며
    -0.06
     unveiled
    -0.06
     ultimo
    -0.06
     generals
    -0.06
    POSITIVE LOGITS
    phot
    0.07
     Susan
    0.06
    GetWidth
    0.06
     Sheriff
    0.06
     RTVF
    0.06
     SJ
    0.06
     Wheat
    0.06
    hp
    0.06
     POSSIBILITY
    0.06
    .Atoi
    0.06
    Act Density 0.001%

    No Known Activations