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

    Neuronpedia

    INDEX
    Explanations

    low

    np_max-act · gemini-2.0-flash

    The neuron fires on narrative cues that describe how someone is speaking—adverbs and descriptors of vocal delivery like “slowly,” “low,” “whisper,” or “leaned in.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Paz
    -0.06
     Israelis
    -0.06
    ekt
    -0.06
    adt
    -0.06
    -rock
    -0.06
    'h
    -0.05
     Quantity
    -0.05
     driv
    -0.05
     Increasing
    -0.05
     Hiện
    -0.05
    POSITIVE LOGITS
     deviceId
    0.08
    _UPDATE
    0.06
    .Enable
    0.06
    .IsNull
    0.06
     dateFormatter
    0.06
     závě
    0.06
     onItemClick
    0.06
    .Trace
    0.06
     Requires
    0.06
     مو
    0.06
    Act Density 0.003%

    No Known Activations