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

    Neuronpedia

    INDEX
    Explanations

    .in

    np_max-act · gemini-2.0-flash

    This neuron detects references to template/configuration filenames ending in “.in” (e.g. Makefile.in, foo.pc.in) in diff and build‐script contexts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Sophie
    -0.06
     shar
    -0.06
     ön
    -0.06
    팔
    -0.06
     свобод
    -0.06
     Automated
    -0.06
     Move
    -0.06
     Satellite
    -0.06
     TTL
    -0.06
     credentials
    -0.06
    POSITIVE LOGITS
     своим
    0.07
    =item
    0.07
     aslında
    0.06
    ара
    0.06
    0.06
    [keys
    0.06
    cerpt
    0.06
    uese
    0.06
     invention
    0.06
    rvine
    0.06
    Act Density 0.001%

    No Known Activations