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

    Neuronpedia

    INDEX
    Explanations

    finding commonalities

    np_max-act · gemini-2.0-flash

    The neuron chiefly activates on numeric tokens (digits, measurements, and decimal‐number fragments) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     conveying
    -0.07
    .mid
    -0.06
    INF
    -0.06
    SharedPtr
    -0.06
    itory
    -0.06
    carrier
    -0.06
     Bonnie
    -0.06
     semaphore
    -0.06
     deterrent
    -0.06
     Athe
    -0.06
    POSITIVE LOGITS
     γρα
    0.06
    ocos
    0.06
     نقش
    0.06
     avent
    0.06
     differ
    0.06
     Yemen
    0.06
    apiKey
    0.06
    (lista
    0.06
     bulunduğu
    0.06
    0.06
    Act Density 0.060%

    No Known Activations