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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    The neuron detects content-bearing topic words in questions—especially the noun or key term that follows interrogative cues like “what kind of.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    mix
    -0.07
    .rx
    -0.07
    PP
    -0.06
     three
    -0.06
     cruc
    -0.06
     resolves
    -0.06
    маг
    -0.06
    was
    -0.06
     humour
    -0.06
     resolutions
    -0.06
    POSITIVE LOGITS
     التش
    0.07
    .TypeOf
    0.07
    leader
    0.07
    ".$_
    0.07
    (delete
    0.06
     Freak
    0.06
     fileInfo
    0.06
    /shop
    0.06
     Which
    0.06
     kindly
    0.06
    Act Density 0.010%

    No Known Activations