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

    Neuronpedia

    INDEX
    Explanations

    code syntax

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric literal tokens (particularly floating‐point constants) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     cryptocurrency
    -0.07
     Xia
    -0.07
     analyzed
    -0.06
     дослідження
    -0.06
    (ss
    -0.06
    tournament
    -0.06
    /.
    -0.06
    存档
    -0.06
     наход
    -0.06
    ifikace
    -0.06
    POSITIVE LOGITS
     ilet
    0.07
     leave
    0.06
    .prevent
    0.06
     bert
    0.06
     вод
    0.06
     tách
    0.06
     candles
    0.06
    μβ
    0.06
    quisition
    0.06
    .getCell
    0.06
    Act Density 0.011%

    No Known Activations