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

    Neuronpedia

    INDEX
    Explanations

    iness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _TRANSFORM
    -0.07
    (VALUE
    -0.07
    acula
    -0.06
    unks
    -0.06
    ména
    -0.06
    .Named
    -0.06
    Wildcard
    -0.06
    Assignment
    -0.06
    leştir
    -0.06
    朋
    -0.06
    POSITIVE LOGITS
     OCR
    0.12
    urry
    0.11
     Trojan
    0.08
    _CENTER
    0.07
    ocr
    0.07
    INESS
    0.07
    ٢
    0.07
     Status
    0.07
     status
    0.07
     confidence
    0.06
    Act Density 0.003%

    No Known Activations