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

    Neuronpedia

    INDEX
    Explanations

    Parenthesis and commas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    笑声
    -0.07
     الحقيقي
    -0.07
    คณะ
    -0.07
    뼝
    -0.07
     encyclopedia
    -0.06
     yayın
    -0.06
    jen
    -0.06
     istedi
    -0.06
    _accel
    -0.06
    挺
    -0.06
    POSITIVE LOGITS
     Crate
    0.08
    bad
    0.07
    "That
    0.07
    -prom
    0.07
     oci
    0.07
    every
    0.07
     hy
    0.07
     spat
    0.06
    Tickets
    0.06
    גג
    0.06
    Act Density 0.063%

    No Known Activations