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

    Neuronpedia

    INDEX
    Explanations

    eye contact

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     પગ
    0.42
    riding
    0.42
    ruch
    0.41
    ARMA
    0.41
    Turbo
    0.40
     গায়ে
    0.40
    UMA
    0.39
    TIMESTAMPDIFF
    0.39
    arming
    0.39
    Silence
    0.39
    POSITIVE LOGITS
     👀
    0.98
     gaze
    0.95
     sockets
    0.94
     squint
    0.88
     socket
    0.85
    👁
    0.80
     gazed
    0.79
     lids
    0.78
     gazing
    0.77
     blinked
    0.77
    Act Density 0.039%

    No Known Activations