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

    Neuronpedia

    INDEX
    Explanations

    technical and programming terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     %><%=
    0.45
    と思いますが
    0.40
    -
    0.39
    かもしれませんが
    0.38
    +,
    0.38
    いますが
    0.37
     डेयरी
    0.36
    হীন
    0.36
    '=>'','
    0.36
    शियल
    0.35
    POSITIVE LOGITS
    。
    0.59
    }$.
    0.48
     ہے۔
    0.47
    .}
    0.45
    。)
    0.45
    .}$
    0.45
     ។
    0.45
    .<
    0.44
    .\\
    0.42
    .)
    0.41
    Act Density 0.170%

    No Known Activations