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

    Neuronpedia

    INDEX
    Explanations

    Prepositions and articles

    np_max-act · gemini-2.0-flash

    This neuron selectively activates on numeric tokens representing floating‐point numbers (i.e. sequences containing a decimal point).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     meth
    -0.06
    hung
    -0.06
     extend
    -0.06
    _WARN
    -0.06
     installer
    -0.06
     duplication
    -0.06
     bikes
    -0.06
    opi
    -0.06
    eti
    -0.06
    (client
    -0.06
    POSITIVE LOGITS
    .bitmap
    0.07
    AlmostEqual
    0.07
     노래
    0.07
    vů
    0.07
    _LIMIT
    0.06
     рядом
    0.06
     ForeignKey
    0.06
    .load
    0.06
     خوان
    0.06
    -->
↵
    0.06
    Act Density 0.040%

    No Known Activations