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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash

    The neuron spots floating‐point numeric literals (numbers containing a decimal point).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ongo
    -0.08
    �
    -0.07
    (percent
    -0.07
     Enterprises
    -0.07
    oggle
    -0.07
     franc
    -0.07
    이비
    -0.07
    _SELECT
    -0.07
    .Invariant
    -0.07
     Cic
    -0.06
    POSITIVE LOGITS
    άλυψης
    0.06
    Од
    0.06
    編
    0.06
     Callable
    0.06
     deadlock
    0.06
     darkest
    0.06
    。大
    0.06
     商
    0.05
    -changing
    0.05
    чем
    0.05
    Act Density 0.012%

    No Known Activations