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
     关
    -0.07
    Ａ
    -0.07
    ея
    -0.06
    ujeme
    -0.06
     الخام
    -0.06
    @section
    -0.06
     vů
    -0.06
    <Menu
    -0.06
    uje
    -0.06
     chương
    -0.06
    POSITIVE LOGITS
    .coeff
    0.07
    ivals
    0.07
     guardians
    0.07
    북
    0.06
     ApiException
    0.06
    fest
    0.06
    signed
    0.06
    hlen
    0.06
    deniz
    0.06
     pis
    0.06
    Act Density 0.000%

    No Known Activations