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

    Neuronpedia

    INDEX
    Explanations

    reform

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     welche
    -0.06
     δεδο
    -0.06
     деся
    -0.06
     przy
    -0.06
    Qu
    -0.06
    láš
    -0.06
     từng
    -0.06
     bunları
    -0.06
     dosud
    -0.06
     thunder
    -0.06
    POSITIVE LOGITS
    .Argument
    0.07
     militant
    0.07
    وث
    0.07
    ertext
    0.06
    олет
    0.06
    招聘
    0.06
     gcd
    0.06
     Как
    0.06
    rpc
    0.06
    الف
    0.06
    Act Density 0.002%

    No Known Activations