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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash

    This neuron detects chemical compound names that include numeric locants and hyphens (e.g. “3,6-lactone” in D-glucurono-3,6-lactone”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    enge
    -0.06
    .say
    -0.06
     rdf
    -0.06
     coppia
    -0.06
    Solo
    -0.06
    textbox
    -0.06
    _ZERO
    -0.06
    Dice
    -0.06
    cookie
    -0.06
    navigator
    -0.06
    POSITIVE LOGITS
    .</
    0.07
     Sonata
    0.07
    ट
    0.06
    _;↵
    0.06
    (rv
    0.06
    ục
    0.06
    /check
    0.06
    NSError
    0.06
    .Level
    0.06
     vš
    0.06
    Act Density 0.028%

    No Known Activations