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

    Neuronpedia

    INDEX
    Explanations

    complex, formal writing

    np_max-act · gemini-2.0-flash

    This neuron responds to longer, multi-syllabic content words (e.g. “operating,” “utilize,” “various”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    'ex
    -0.07
     sometime
    -0.07
     Foot
    -0.07
     IB
    -0.07
    _f
    -0.07
    treeview
    -0.06
    не
    -0.06
     glyphs
    -0.06
     Summary
    -0.06
     tests
    -0.06
    POSITIVE LOGITS
     gameObject
    0.07
    covers
    0.06
    ทย
    0.06
     relying
    0.06
    랜
    0.06
     První
    0.06
     eater
    0.06
     října
    0.05
    MFLOAT
    0.05
    \Base
    0.05
    Act Density 0.162%

    No Known Activations