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

    Neuronpedia

    INDEX
    Explanations

    Unicode subscripts and superscripts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ్యాచ్
    0.47
     dugg
    0.42
    CString
    0.39
     Ceren
    0.39
    prising
    0.38
    ⣶
    0.37
    ள்ளது
    0.37
    webContents
    0.36
    ثله
    0.36
    覦
    0.35
    POSITIVE LOGITS
    éto
    0.39
     tlač
    0.38
    vič
    0.37
    ko
    0.37
     aritmética
    0.37
    array
    0.37
    <0x8B>
    0.36
    锤
    0.36
    Ⅲ
    0.36
    hammer
    0.36
    Act Density 0.003%

    No Known Activations