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

    Neuronpedia

    INDEX
    Explanations

    {{

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    *
↵
    -0.08
     Utah
    -0.07
     cuis
    -0.07
     Kolkata
    -0.07
    ArrayType
    -0.07
     Paz
    -0.07
    EM
    -0.07
     PURE
    -0.07
    YSQL
    -0.06
     ліка
    -0.06
    POSITIVE LOGITS
     acting
    0.06
     synthesis
    0.06
     Russell
    0.06
     کار
    0.06
    下载
    0.06
    ajan
    0.06
     composing
    0.06
    總
    0.06
     backbone
    0.06
     pornô
    0.06
    Act Density 0.001%

    No Known Activations