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

    Neuronpedia

    INDEX
    Explanations

    _

    np_max-act · gemini-2.0-flash

    The neuron detects C/C++ header‐guard macro names (the “#ifndef …_H_” identifiers at the top of header files).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ()='
    -0.07
     replies
    -0.07
     gas
    -0.07
     düş
    -0.06
    ozy
    -0.06
    -cap
    -0.06
    ModelError
    -0.06
    FTA
    -0.06
     Gas
    -0.06
    rends
    -0.06
    POSITIVE LOGITS
    '''
↵
    0.07
     intermitt
    0.06
    (pair
    0.06
     Foundation
    0.06
     precisely
    0.06
    /or
    0.06
    [m
    0.06
     nail
    0.06
    .Azure
    0.05
     Injector
    0.05
    Act Density 0.000%

    No Known Activations