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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric literals with decimal points (i.e. floating‐point numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     expiry
    -0.07
     mam
    -0.06
    platform
    -0.06
     тов
    -0.06
    highest
    -0.06
    Probe
    -0.06
    ré
    -0.06
    -stock
    -0.06
     observer
    -0.06
     skeleton
    -0.06
    POSITIVE LOGITS
     jednání
    0.07
     적
    0.06
     Xperia
    0.06
     FName
    0.06
    [it
    0.06
    evi
    0.06
     yerinde
    0.06
    .Scroll
    0.06
     Finch
    0.06
    _WAIT
    0.06
    Act Density 0.089%

    No Known Activations