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

    Neuronpedia

    INDEX
    Explanations

    else

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nie
    -0.07
     presidents
    -0.07
     Haupt
    -0.07
     Männer
    -0.07
    بوب
    -0.06
     zw
    -0.06
     खर
    -0.06
    шив
    -0.06
    706
    -0.06
     bree
    -0.06
    POSITIVE LOGITS
    }↵↵↵↵↵↵
    0.07
     fals
    0.07
    표
    0.07
    template
    0.07
    CrLf
    0.07
    horizontal
    0.07
    ete
    0.07
    ↵↵↵↵↵↵↵
    0.07
    OptionsResolver
    0.07
    ,date
    0.06
    Act Density 0.012%

    No Known Activations