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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tart
    -0.07
     spelling
    -0.06
     nominal
    -0.06
    美妆
    -0.06
    drag
    -0.06
    爐
    -0.06
     giảng
    -0.06
    soft
    -0.06
     fixing
    -0.06
    luck
    -0.06
    POSITIVE LOGITS
    .Web
    0.08
    .view
    0.07
    .getDocument
    0.07
    .Claims
    0.07
     persona
    0.07
    (identifier
    0.07
    beam
    0.07
    .Print
    0.07
     An
    0.06
    Membership
    0.06
    Act Density 0.003%

    No Known Activations