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

    Neuronpedia

    INDEX
    Explanations

    memory allocation

    np_max-act · gemini-2.0-flash

    The neuron fires on any token containing “alloc” (e.g. names of alloc/allocate/realloc/free routines, allocator types, or related macros).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    enne
    -0.07
    _constraint
    -0.07
     passengers
    -0.07
    =sub
    -0.07
     passenger
    -0.07
     mensaje
    -0.06
    .getRandom
    -0.06
     returns
    -0.06
    (feed
    -0.06
    ,address
    -0.06
    POSITIVE LOGITS
     dealloc
    0.08
    ادر
    0.08
    _alloc
    0.08
    alloc
    0.07
    malloc
    0.07
    wik
    0.07
    _ALLOC
    0.07
     Alloc
    0.07
    Malloc
    0.07
    realloc
    0.07
    Act Density 0.004%

    No Known Activations