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

    Neuronpedia

    INDEX
    Explanations

    bored expression

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ilable
    0.75
    र्क
    0.74
    চিৎ
    0.72
     workflows
    0.70
     धूमधाम
    0.70
    decorators
    0.69
     hashlib
    0.65
    Fallback
    0.65
     플랫폼
    0.65
     dplyr
    0.64
    POSITIVE LOGITS
     eyes
    2.04
     gaze
    1.96
     Eyes
    1.73
     stare
    1.66
    Eyes
    1.63
     eye
    1.63
    eyes
    1.62
     mirada
    1.62
    眼神
    1.61
     gazing
    1.54
    Act Density 0.600%

    No Known Activations