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

    Neuronpedia

    INDEX
    Explanations

    dash symbol

    np_max-act · gemini-2.0-flash

    The neuron fires on standalone dash-prefixed option flags (e.g. “-e”, “-ev”, “-eo”, “-ex”) in shell scripts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .Stack
    -0.07
     defenses
    -0.07
     ощ
    -0.07
    .say
    -0.07
    Confirmation
    -0.07
    รายการ
    -0.07
    Professional
    -0.07
    .'));↵
    -0.07
     distinguished
    -0.07
    cp
    -0.07
    POSITIVE LOGITS
    itech
    0.06
    youtube
    0.06
     θα
    0.06
     celle
    0.06
     bele
    0.06
    .lineTo
    0.06
    _journal
    0.06
     CURLOPT
    0.06
    _BITMAP
    0.05
     enthusi
    0.05
    Act Density 0.000%

    No Known Activations