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

    Neuronpedia

    INDEX
    Explanations

    touch

    np_max-act · gemini-2.0-flash

    This neuron detects explicit sensory-descriptive words (touch, taste, smell, sound, texture, feel, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Ward
    -0.06
    wrap
    -0.06
     Industrial
    -0.06
     установки
    -0.06
    Resource
    -0.06
    cfg
    -0.06
    환경
    -0.06
    UBY
    -0.06
    Scripts
    -0.06
     organ
    -0.06
    POSITIVE LOGITS
     sucked
    0.07
     controle
    0.07
     tiến
    0.07
     Ubisoft
    0.06
     radically
    0.06
     jako
    0.06
     thems
    0.06
     Narendra
    0.06
     Bermuda
    0.06
     difer
    0.06
    Act Density 0.003%

    No Known Activations