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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    The neuron detects numeric tokens containing decimal points (i.e., floating-point figures).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _ACTIONS
    -0.06
     trees
    -0.06
     tree
    -0.06
     syntax
    -0.06
    .coroutines
    -0.06
     CircularProgressIndicator
    -0.06
     birinin
    -0.06
     binds
    -0.06
    .getP
    -0.06
    ктів
    -0.06
    POSITIVE LOGITS
    (tasks
    0.07
     бюджет
    0.07
    LOCAL
    0.07
    $template
    0.07
     Metro
    0.07
    [arr
    0.06
     ($.
    0.06
     Monthly
    0.06
     euro
    0.06
    Premium
    0.06
    Act Density 0.039%

    No Known Activations