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

    Neuronpedia

    INDEX
    Explanations

    separators

    np_max-act · gemini-2.0-flash

    The neuron detects interactive‐fiction choice or branching markers (like “||” and “>>”) that introduce player options or script directives.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ※
    -0.06
     کم
    -0.06
     focused
    -0.06
    edla
    -0.06
    XObject
    -0.06
     $↵↵
    -0.06
    حات
    -0.06
    	put
    -0.06
    ace
    -0.06
     стра
    -0.05
    POSITIVE LOGITS
    샤
    0.07
    STRUCTION
    0.07
     transformers
    0.07
    เคราะห
    0.07
     Restaurant
    0.06
    ChangeEvent
    0.06
     Можно
    0.06
    0.06
     rugged
    0.06
    _similarity
    0.06
    Act Density 0.005%

    No Known Activations