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

    Neuronpedia

    INDEX
    Explanations

    touch

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Grant
    -0.08
    ario
    -0.07
    ewart
    -0.07
     Clan
    -0.07
     slate
    -0.07
    Ja
    -0.07
    Grant
    -0.07
     určit
    -0.07
     Keller
    -0.06
    Jwt
    -0.06
    POSITIVE LOGITS
     touches
    0.14
     Touch
    0.14
     touch
    0.14
     touched
    0.12
     touching
    0.11
    Touch
    0.10
    touch
    0.10
    -touch
    0.10
     TOUCH
    0.10
     untouched
    0.09
    Act Density 0.015%

    No Known Activations