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

    Neuronpedia

    INDEX
    Explanations

    Hexadecimal/Decimal Definitions

    np_max-act · gemini-2.0-flash

    This neuron activates on C-style macro or constant identifiers—i.e. sequences of uppercase letters (and underscores/numbers) used in code definitions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    дав
    -0.06
     TIMES
    -0.06
     coordination
    -0.06
     fac
    -0.06
     sensual
    -0.06
     correctness
    -0.06
    -guide
    -0.06
     двух
    -0.06
     experiences
    -0.06
    ोक
    -0.06
    POSITIVE LOGITS
     Container
    0.07
    ｿ
    0.07
    ليزية
    0.07
     Olivia
    0.07
     avril
    0.07
    Reverse
    0.07
     astore
    0.06
     MediaType
    0.06
    aryawan
    0.06
     Setting
    0.06
    Act Density 0.006%

    No Known Activations