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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash

    This neuron activates primarily on floating‐point decimal numbers (i.e., tokens containing “.” between digits).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Sight
    -0.06
    oid
    -0.06
    .InputStream
    -0.06
    <Menu
    -0.06
    _ASYNC
    -0.06
    tracks
    -0.06
     상담
    -0.06
     Μά
    -0.06
     findBy
    -0.05
    _calls
    -0.05
    POSITIVE LOGITS
     особ
    0.07
     olmam
    0.07
     funciona
    0.07
    ROT
    0.07
     reinforcing
    0.07
     projev
    0.06
    aştır
    0.06
     sanitizer
    0.06
    еч
    0.06
    /configuration
    0.06
    Act Density 0.018%

    No Known Activations