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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash

    This neuron activates on decimal numeric literals (floating‐point numbers) in license/comment headers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    τεύ
    -0.07
     मण
    -0.07
    DISPLAY
    -0.07
     hã
    -0.06
     to
    -0.06
     أ
    -0.06
    icals
    -0.06
     relaxing
    -0.06
     Mons
    -0.06
    ,#
    -0.06
    POSITIVE LOGITS
    ","
    0.06
    Definition
    0.06
     samozřejmě
    0.06
    Sky
    0.06
    侵
    0.06
    �
    0.06
    ıyorlar
    0.05
    Road
    0.05
    724
    0.05
    .Down
    0.05
    Act Density 0.001%

    No Known Activations