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

    Neuronpedia

    INDEX
    Explanations

    physical contact or perception

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ၀၀
    0.76
    )：
    0.72
    )।
    0.70
    %。
    0.70
    魧
    0.69
    )^{*}
    0.67
    ୦
    0.67
    )。
    0.66
    JG
    0.66
     ಯಾವಾಗ
    0.66
    POSITIVE LOGITS
     touch
    1.10
     Touch
    1.06
    ↵
    0.98
    h
    0.97
    Touch
    0.95
     TOUCH
    0.95
    touch
    0.93
    Touching
    0.88
     touched
    0.86
     touching
    0.85
    Act Density 0.019%

    No Known Activations