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

    Neuronpedia

    INDEX
    Explanations

    colons

    np_max-act · gemini-2.0-flash

    This neuron detects editor modeline or file-local settings lines (e.g. “-*- Mode: …; tab-width: … -*-”) that configure coding style.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ear
    -0.07
    aned
    -0.07
    股
    -0.07
     headset
    -0.06
    -To
    -0.06
    pis
    -0.06
    peaker
    -0.06
    lost
    -0.06
    월
    -0.06
     Pes
    -0.06
    POSITIVE LOGITS
     createTime
    0.07
    _GT
    0.06
    ％
    0.06
    MainThread
    0.06
    QUIRE
    0.06
     chlorine
    0.06
    .serialization
    0.06
    ");//
    0.06
    unfinished
    0.06
    unsqueeze
    0.06
    Act Density 0.000%

    No Known Activations