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

    Neuronpedia

    INDEX
    Explanations

    action

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SDS
    -0.09
     leans
    -0.07
     resisted
    -0.07
     mixes
    -0.07
    filtr
    -0.06
     mol
    -0.06
     Redemption
    -0.06
    -Saharan
    -0.06
    ventario
    -0.06
    امل
    -0.06
    POSITIVE LOGITS
    246
    0.07
     определя
    0.07
     sông
    0.06
     şark
    0.06
     política
    0.06
     khác
    0.06
    上海
    0.06
     Coleman
    0.06
     дал
    0.06
     Друг
    0.06
    Act Density 0.013%

    No Known Activations