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

    Neuronpedia

    INDEX
    Explanations

    Compiler flags

    np_max-act · gemini-2.0-flash

    The neuron fires on build‐system variable names related to compiler or linker flags (e.g. CFLAGS, CPPFLAGS, LDFLAGS).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     CreateUser
    -0.07
     koneč
    -0.07
    =Math
    -0.06
    abyrinth
    -0.06
     growers
    -0.06
    fortunately
    -0.06
     Marie
    -0.06
     Cout
    -0.06
    	ax
    -0.06
    _tmp
    -0.06
    POSITIVE LOGITS
     остан
    0.07
    �
    0.07
     дев
    0.06
    FLAGS
    0.06
    <Message
    0.06
    s
    0.06
     emacs
    0.06
    .native
    0.06
    ･･
    0.06
     subsidi
    0.06
    Act Density 0.003%

    No Known Activations