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

    Neuronpedia

    INDEX
    Explanations

    Typos/code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     терап
    -0.07
    widgets
    -0.07
    istributed
    -0.07
     terrorism
    -0.06
    诊
    -0.06
     Nicar
    -0.06
    etrics
    -0.06
    expr
    -0.06
     entrada
    -0.06
     هیچ
    -0.06
    POSITIVE LOGITS
     appro
    0.07
    òng
    0.07
     access
    0.06
     перер
    0.06
    reported
    0.06
     worldview
    0.06
    anyl
    0.06
    Arizona
    0.06
     cette
    0.06
    %↵↵
    0.06
    Act Density 0.183%

    No Known Activations