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

    Neuronpedia

    INDEX
    Explanations

    political freedom and encoding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ö
    0.44
    ])
    0.43
    r
    0.43
    (
    0.42
    in
    0.42
    infer
    0.42
    imte
    0.42
    el
    0.42
    ifice
    0.42
    stones
    0.41
    POSITIVE LOGITS
    ମ୍
    0.42
    䟧
    0.42
     encoding
    0.41
    বলে
    0.40
    Clinton
    0.39
    飴
    0.39
    杪
    0.38
     Gifford
    0.38
    Encode
    0.38
     Encode
    0.38
    Act Density 0.000%

    No Known Activations