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

    Neuronpedia

    INDEX
    Explanations

    Providing assistance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (App
    -0.06
    fang
    -0.06
    clip
    -0.06
     smlouvy
    -0.06
    цький
    -0.06
    (pb
    -0.06
    venting
    -0.06
     reduces
    -0.06
    (concat
    -0.06
    enschaft
    -0.06
    POSITIVE LOGITS
    095
    0.07
    MethodName
    0.06
    ична
    0.06
    IMIZE
    0.06
     ประก
    0.06
    .toJSONString
    0.06
    ежать
    0.06
     caf
    0.06
    不得
    0.06
    which
    0.06
    Act Density 0.017%

    No Known Activations