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

    Neuronpedia

    INDEX
    Explanations

    This can be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ÂĢÂĢ
    -0.09
    езÑĥлÑĮÑĤ
    -0.09
    -alist
    -0.09
    ¶Į
    -0.09
    ¦æĥħ
    -0.09
    ıa
    -0.08
    įng
    -0.08
    /Dk
    -0.08
    _WS
    -0.08
    ¨ë¶Ģ
    -0.08
    POSITIVE LOGITS
     :.
    0.08
    %C
    0.08
    aign
    0.08
     -
    0.08
     simples
    0.08
     Ire
    0.07
    [,]
    0.07
     tainted
    0.07
     Bearings
    0.07
    ÃŁer
    0.07
    Act Density 0.328%

    No Known Activations