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

    Neuronpedia

    INDEX
    Explanations

    cors configuration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    y
    1.20
    o
    1.16
    i
    1.12
    ]
    1.06
    ي
    0.97
    י
    0.92
    it
    0.90
    จะ
    0.87
    '
    0.86
    ”
    0.86
    POSITIVE LOGITS
    cors
    1.12
    Cors
    0.97
    corper
    0.94
    ला
    0.88
    ሳሪያ
    0.85
    ྪ
    0.84
     CORS
    0.83
    ٧
    0.82
     Cors
    0.80
     Corse
    0.80
    Act Density 0.001%

    No Known Activations