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

    Neuronpedia

    INDEX
    Explanations

    Formal writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    song
    -0.06
    nick
    -0.06
    pickup
    -0.06
    applicant
    -0.06
    .orders
    -0.06
     reminded
    -0.06
    being
    -0.06
     nec
    -0.06
    abouts
    -0.06
     bun
    -0.06
    POSITIVE LOGITS
     Kent
    0.06
     squeeze
    0.06
     Dise
    0.06
     صالح
    0.06
     відбува
    0.06
     出
    0.06
    刑
    0.06
     tqdm
    0.06
     db
    0.06
     فلس
    0.06
    Act Density 0.042%

    No Known Activations