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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     erect
    -0.06
    كان
    -0.06
     SAFE
    -0.06
     Sevent
    -0.06
    007
    -0.06
    NEG
    -0.06
    spe
    -0.06
    $search
    -0.06
     aluno
    -0.06
     welt
    -0.06
    POSITIVE LOGITS
    street
    0.07
    無し
    0.06
    ([])↵
    0.06
     Ün
    0.06
     τη
    0.06
     Ans
    0.06
     ω
    0.06
    ып
    0.06
    тим
    0.06
     hooked
    0.06
    Act Density 0.001%

    No Known Activations