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

    Neuronpedia

    INDEX
    Explanations

    scientific/technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pett
    -0.06
    dq
    -0.06
    ume
    -0.06
     Jeff
    -0.06
    �
    -0.06
    ẹ
    -0.06
    Ju
    -0.06
     thuật
    -0.06
    hek
    -0.06
    .Transfer
    -0.05
    POSITIVE LOGITS
    (variable
    0.07
     deflect
    0.07
    TargetException
    0.07
    (email
    0.07
     outlier
    0.07
    罪
    0.06
    TypeID
    0.06
     subsid
    0.06
    (span
    0.06
    (model
    0.06
    Act Density 0.165%

    No Known Activations