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

    Neuronpedia

    INDEX
    Explanations

    gaze, stare, glance, eyes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enced
    0.46
    APPEND
    0.41
    早い
    0.41
    벼
    0.40
    flatMap
    0.40
    gzip
    0.39
    sterling
    0.39
    appending
    0.39
    sounding
    0.38
    cancel
    0.38
    POSITIVE LOGITS
     gaze
    0.86
     stare
    0.82
     mirada
    0.82
     stares
    0.78
     gazing
    0.75
     glance
    0.73
     gazed
    0.73
     glances
    0.72
    目光
    0.71
     eyes
    0.70
    Act Density 0.060%

    No Known Activations