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

    Neuronpedia

    INDEX
    Explanations

    /config

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    見て
    -0.08
    indh
    -0.08
     taxonomy
    -0.07
    ⌧
    -0.07
    寐
    -0.07
    arefa
    -0.07
    鲰
    -0.07
     summar
    -0.07
    胫
    -0.07
    三四
    -0.07
    POSITIVE LOGITS
    Я
    0.08
    Will
    0.07
     운
    0.07
    ()][
    0.07
     experiments
    0.06
    Փ
    0.06
    Media
    0.06
    ﴾
    0.06
    Inputs
    0.06
    페이지
    0.06
    Act Density 0.001%

    No Known Activations