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

    Neuronpedia

    INDEX
    Explanations

    user

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Junction
    -0.09
     Staffing
    -0.08
     revisions
    -0.08
    gestelde
    -0.08
     Sympathy
    -0.08
    <button
    -0.08
     colossal
    -0.08
     mouths
    -0.08
     jaws
    -0.08
    Synopsis
    -0.08
    POSITIVE LOGITS
     ~/.
    0.14
     personal
    0.12
    个人
    0.11
     pessoais
    0.11
     personnelles
    0.11
     개인
    0.11
     individual's
    0.11
    HOME
    0.10
     HOME
    0.10
    (usuario
    0.10
    Act Density 0.008%

    No Known Activations