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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    preferences
    -0.07
    فاع
    -0.07
    Texture
    -0.07
    OWN
    -0.06
    'яз
    -0.06
    ;",↵
    -0.06
    حي
    -0.06
    MONTH
    -0.06
    range
    -0.06
    ertainment
    -0.06
    POSITIVE LOGITS
     authService
    0.07
    /MIT
    0.07
    대의
    0.06
     wiel
    0.06
     çıktı
    0.06
    .An
    0.06
     그가
    0.06
     nebylo
    0.06
    .microsoft
    0.06
     painfully
    0.06
    Act Density 0.209%

    No Known Activations