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

    Neuronpedia

    INDEX
    Explanations

    Touch

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the literal token “Touch” (as in “Cocoa Touch” or “Interface Builder Cocoa Touch”) in the XML.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    icao
    -0.07
    .Clear
    -0.06
     berlin
    -0.06
    やる
    -0.06
     protocols
    -0.06
     sulfur
    -0.06
    Vars
    -0.06
    print
    -0.06
    基
    -0.06
     ocean
    -0.06
    POSITIVE LOGITS
     TOUCH
    0.09
    Touch
    0.09
    -touch
    0.08
     Touch
    0.07
    tiv
    0.07
    จำหน
    0.07
     tactile
    0.07
    touch
    0.07
    rush
    0.07
    conj
    0.06
    Act Density 0.001%

    No Known Activations