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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    The neuron is detecting floating‐point numeric tokens (i.e. decimal numbers with a “.”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Person
    -0.07
    LP
    -0.06
     Puerto
    -0.06
     GPL
    -0.06
    ocaust
    -0.06
    :H
    -0.06
     tourist
    -0.06
    _pr
    -0.06
     VERSION
    -0.06
    灵
    -0.06
    POSITIVE LOGITS
     onions
    0.07
    _DEC
    0.06
     salv
    0.06
    rbrace
    0.06
     weekday
    0.06
     #-}↵↵
    0.06
     yatırım
    0.06
     nymph
    0.06
    .dst
    0.06
    December
    0.06
    Act Density 0.005%

    No Known Activations