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

    Neuronpedia

    INDEX
    Explanations

    Sentence fragments

    np_max-act · gemini-2.0-flash

    This neuron selectively activates on subword tokens that are parts of floating-point numbers (decimal fractions).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _coordinates
    -0.07
    ToLeft
    -0.07
    _REFERENCE
    -0.07
    Texture
    -0.07
    ANDLE
    -0.06
     tbl
    -0.06
    |}↵
    -0.06
    .keyboard
    -0.06
    typeorm
    -0.06
     disable
    -0.06
    POSITIVE LOGITS
     باشگاه
    0.07
     nargin
    0.06
     gaps
    0.06
     вам
    0.06
    mouth
    0.06
    �
    0.06
    asyon
    0.06
     frustrations
    0.06
     ativ
    0.06
    (cert
    0.06
    Act Density 0.024%

    No Known Activations