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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on uses of the C/C++ pointer‐member access operator “→” (i.e. the “->” arrow for dereferencing struct/class pointers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    code and structures related to software development and implementation.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .adapter
    -0.08
     zend
    -0.07
     物
    -0.06
    生命
    -0.06
     nejd
    -0.06
    ye
    -0.06
     Neville
    -0.06
     boils
    -0.06
     미국
    -0.06
     sư
    -0.06
    POSITIVE LOGITS
    xDF
    0.06
    อย
    0.06
    secs
    0.06
    PostBack
    0.06
    $time
    0.06
    igm
    0.06
     Full
    0.06
     linha
    0.06
    udio
    0.06
     securely
    0.06
    Act Density 0.025%

    No Known Activations