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

    Neuronpedia

    INDEX
    Explanations

    directing gaze

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sounds
    0.38
     CALLBACK
    0.36
    Sounds
    0.36
    avier
    0.35
    sounds
    0.34
     gehörte
    0.34
    िओ
    0.33
    Calling
    0.33
    echo
    0.32
    abling
    0.32
    POSITIVE LOGITS
     intently
    0.86
     stare
    0.82
    看向
    0.72
     staring
    0.70
     stares
    0.69
     stared
    0.67
     gazed
    0.66
     gazing
    0.64
     gaze
    0.62
     👀
    0.62
    Act Density 0.031%

    No Known Activations