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

    Neuronpedia

    INDEX
    Explanations

    surrounding scope

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ♠
    0.42
    interpolate
    0.40
    ef
    0.39
    gawa
    0.39
    ou
    0.38
    쑤
    0.38
    iam
    0.38
    bib
    0.37
    emper
    0.37
    dick
    0.37
    POSITIVE LOGITS
     sectoral
    0.39
    ULONG
    0.39
    врат
    0.39
     "]");
    0.38
     annoyance
    0.37
     वोल्टेज
    0.36
    された
    0.36
    டல்
    0.36
     canes
    0.36
    /}{
    0.35
    Act Density 0.002%

    No Known Activations