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

    Neuronpedia

    INDEX
    Explanations

    FreeType code headers

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of floating-point numeric literals (decimal numbers) in the comment headers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    hel
    -0.08
     DRAW
    -0.07
     onLoad
    -0.07
     stre
    -0.07
     Jackson
    -0.07
     body
    -0.07
     diffusion
    -0.07
     Abdul
    -0.06
     Changed
    -0.06
     died
    -0.06
    POSITIVE LOGITS
    ा।
    0.06
     далеко
    0.06
     nghệ
    0.06
              
↵
    0.06
    peaker
    0.06
     >
↵
    0.06
    Whitespace
    0.06
    ası
    0.06
     Taco
    0.06
     hf
    0.06
    Act Density 0.001%

    No Known Activations