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

    Neuronpedia

    INDEX
    Explanations

    emerging

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    wealth
    -0.07
    OfWork
    -0.07
    	comment
    -0.07
    (Attribute
    -0.06
    าอ
    -0.06
     собствен
    -0.06
    nor
    -0.06
     trovare
    -0.06
    [max
    -0.06
     times
    -0.06
    POSITIVE LOGITS
    ))){↵
    0.07
    çuk
    0.07
    кус
    0.06
    .sourceforge
    0.06
    ediği
    0.06
     ख
    0.06
     kre
    0.06
    ุบ
    0.06
    346
    0.06
    udd
    0.06
    Act Density 0.033%

    No Known Activations