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

    Neuronpedia

    INDEX
    Explanations

    presentations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    筑
    -0.07
     psychological
    -0.07
     sic
    -0.07
     çı
    -0.07
    Safety
    -0.07
    esian
    -0.07
    置身
    -0.07
    ethical
    -0.07
    💼
    -0.07
    红酒
    -0.07
    POSITIVE LOGITS
    .evaluate
    0.07
     bund
    0.06
    .iter
    0.06
    .Runtime
    0.06
    翦
    0.06
     final
    0.06
     אשר
    0.06
     أخرى
    0.06
     oferta
    0.06
    𬶠
    0.06
    Act Density 0.000%

    No Known Activations