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

    Neuronpedia

    INDEX
    Explanations

    library

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of compiler/linker library specifications—e.g. tokens like “pkg-config,” “files,” “flags,” “link,” “library,” “LIB,” etc.—that set up and link external libraries.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .lt
    -0.08
    .sul
    -0.07
     gön
    -0.06
     şekl
    -0.06
     userEmail
    -0.06
     ngắn
    -0.06
    _PREF
    -0.06
    .fil
    -0.06
    arb
    -0.06
    );
↵
    -0.06
    POSITIVE LOGITS
     sloppy
    0.06
    UTDOWN
    0.06
     runtime
    0.06
     grey
    0.06
     trains
    0.06
     proud
    0.06
     Inspiration
    0.06
    _pcm
    0.06
    regs
    0.06
    ーパー
    0.06
    Act Density 0.010%

    No Known Activations