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

    Neuronpedia

    INDEX
    Explanations

    Code/Documentation

    np_max-act · gemini-2.0-flash

    This neuron detects command-line option flags (tokens beginning with a hyphen, e.g. “-sV”, “-p”, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ICATION
    -0.07
     Naturally
    -0.06
    establish
    -0.06
    /Framework
    -0.06
    Printf
    -0.06
    .Currency
    -0.06
     resurrect
    -0.06
    (Profile
    -0.06
    kf
    -0.06
     logos
    -0.06
    POSITIVE LOGITS
    .storage
    0.07
     permanent
    0.07
    sd
    0.06
     |[
    0.06
     чис
    0.06
     adına
    0.06
     CAN
    0.06
    .hh
    0.06
    _combine
    0.06
    ::|
    0.06
    Act Density 0.054%

    No Known Activations