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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on numeric tokens—especially floating-point numbers—wherever they appear in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    िच
    -0.07
     prowess
    -0.07
     أي
    -0.07
     исключ
    -0.07
    MHz
    -0.06
     zm
    -0.06
     summarize
    -0.06
    ่างๆ
    -0.06
     especial
    -0.06
     sino
    -0.06
    POSITIVE LOGITS
    /init
    0.06
    :''
    0.06
    (vehicle
    0.06
     Kemp
    0.06
    aos
    0.06
     ForCanBeConvertedToF
    0.06
    .Pin
    0.06
    (#
    0.06
     �
    0.06
    partition
    0.06
    Act Density 0.067%

    No Known Activations