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

    Neuronpedia

    INDEX
    Explanations

    require

    np_max-act · gemini-2.0-flash

    The neuron fires on dependency‐ or requirement‐related field names in package or spec files (e.g. “Depends”, “Requires”, “depend”, “provides”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     parsers
    -0.07
    Acceleration
    -0.07
     $("#"
    -0.06
    chars
    -0.06
    OLEAN
    -0.06
    Absent
    -0.06
    	slot
    -0.06
    ourcem
    -0.06
     yaygın
    -0.06
    ('/')
    -0.06
    POSITIVE LOGITS
    ätzlich
    0.07
    ;
↵
↵
    0.07
     Able
    0.06
     borderline
    0.06
    _BEGIN
    0.06
     Anxiety
    0.06
     Fail
    0.06
    售
    0.06
     &#
    0.06
    ↵
↵
    0.06
    Act Density 0.009%

    No Known Activations