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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash

    the neuron detects numeric tokens and punctuation forming version numbers (e.g. digits and dots).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     tvb
    -0.06
     Araştır
    -0.06
     Circuit
    -0.06
     ilişk
    -0.06
     IOCTL
    -0.06
    _builder
    -0.05
     partir
    -0.05
    _graphics
    -0.05
     ид
    -0.05
     çab
    -0.05
    POSITIVE LOGITS
    pect
    0.07
    worked
    0.06
    .toDouble
    0.06
     corresponding
    0.06
    attach
    0.06
    bol
    0.06
    mtime
    0.06
     sortOrder
    0.06
    	Task
    0.06
    ื
    0.06
    Act Density 0.010%

    No Known Activations