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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    This neuron detects numeric tokens with decimal points, i.e. floating-point numbers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Gonz
    -0.07
     nemá
    -0.07
     уник
    -0.07
    xef
    -0.06
    сам
    -0.06
    .setFont
    -0.06
    541
    -0.06
    �
    -0.06
     Ấn
    -0.06
    ůst
    -0.06
    POSITIVE LOGITS
    slide
    0.07
     polys
    0.06
    oler
    0.06
     ardından
    0.06
     technician
    0.06
     booths
    0.06
    `}↵
    0.06
    _ROOM
    0.06
    slideDown
    0.06
    (""));↵
    0.06
    Act Density 0.038%

    No Known Activations