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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pound
    -0.07
     montage
    -0.06
    ibri
    -0.06
    基地
    -0.06
     hinted
    -0.06
    CHKERRQ
    -0.06
     remarks
    -0.06
    polit
    -0.06
     کلاس
    -0.06
     quotation
    -0.06
    POSITIVE LOGITS
    /App
    0.07
    (delete
    0.07
    breadcrumb
    0.07
     عرضه
    0.06
    (buffer
    0.06
    (man
    0.06
    ียบ
    0.06
    me
    0.06
    ?\
    0.06
    Ann
    0.06
    Act Density 0.008%

    No Known Activations