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

    Neuronpedia

    INDEX
    Explanations

    Conversational writing style

    np_max-act · gemini-2.0-flash

    The neuron broadly activates on ordinary lexical tokens—especially common function words and high‐frequency content words—marking generally “normal” text words.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .icons
    -0.07
    dney
    -0.07
    █
    -0.07
     INDEX
    -0.07
    .userdetails
    -0.07
    (clone
    -0.07
    ً،
    -0.06
    "),
↵
    -0.06
    ltra
    -0.06
    [max
    -0.06
    POSITIVE LOGITS
     casually
    0.06
     resourceId
    0.06
     thiên
    0.06
     โปร
    0.06
    كت
    0.05
    hatt
    0.05
     plagiar
    0.05
    raisal
    0.05
     acidic
    0.05
    SQ
    0.05
    Act Density 0.172%

    No Known Activations