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

    Neuronpedia

    INDEX
    Explanations

    Code analysis/programming

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric literals, especially floating‐point or version numbers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    欣
    -0.07
     příst
    -0.06
    .setBounds
    -0.06
    СР
    -0.06
    _overlap
    -0.06
    imator
    -0.06
    _OLD
    -0.06
     viewer
    -0.06
     azi
    -0.06
    .setError
    -0.06
    POSITIVE LOGITS
    Looper
    0.07
    venge
    0.06
     οι
    0.06
    refer
    0.06
     clit
    0.06
     Nov
    0.06
     printable
    0.06
    Aug
    0.06
    “They
    0.06
    BOOLE
    0.06
    Act Density 0.021%

    No Known Activations