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

    Neuronpedia

    INDEX
    Explanations

    science and mathematics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CGFloat
    -0.07
     disorder
    -0.07
    .What
    -0.06
     Keep
    -0.06
     hoch
    -0.06
    -liter
    -0.06
    pute
    -0.06
     BS
    -0.06
     overwhelm
    -0.06
     иметь
    -0.06
    POSITIVE LOGITS
    Compet
    0.07
     איש
    0.07
    参会
    0.07
    쉘
    0.07
    MethodInfo
    0.07
    ))->
    0.07
    换成
    0.06
    장님
    0.06
    }/>↵
    0.06
     Lily
    0.06
    Act Density 0.037%

    No Known Activations