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

    Neuronpedia

    INDEX
    Explanations

    expectations

    np_max-act · gemini-2.0-flash

    This neuron activates on longer, content-rich words—particularly multi-syllable or high-information tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Stamp
    -0.07
    -risk
    -0.07
    (sound
    -0.07
     спів
    -0.06
    DBObject
    -0.06
     inspection
    -0.06
    Range
    -0.06
    {return
    -0.06
    능
    -0.06
    işti
    -0.06
    POSITIVE LOGITS
    ,start
    0.06
    ream
    0.06
     BUILD
    0.06
     midterm
    0.06
    aimassage
    0.06
    озем
    0.06
    .DEFINE
    0.06
    ]+\
    0.06
    )+(
    0.06
     Views
    0.06
    Act Density 0.043%

    No Known Activations