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

    Neuronpedia

    INDEX
    Explanations

    programming/code

    np_max-act · gemini-2.0-flash

    This neuron never activates—i.e. it doesn’t detect any tokens or patterns (it’s effectively “dead”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    	click
    -0.07
     hairs
    -0.07
     đĩa
    -0.06
     Sort
    -0.06
    KeyType
    -0.06
     Bain
    -0.06
    _HEIGHT
    -0.06
     ماشین
    -0.06
     cams
    -0.06
    asks
    -0.06
    POSITIVE LOGITS
    овали
    0.08
    -item
    0.06
    규
    0.06
    awy
    0.06
     bestimm
    0.06
    щі
    0.06
     conditions
    0.06
     usually
    0.06
    _triggered
    0.06
     personnes
    0.06
    Act Density 0.000%

    No Known Activations