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

    Neuronpedia

    INDEX
    Explanations

    median

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on floating‐point numeric tokens (decimal values) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    coc
    -0.07
     acrylic
    -0.06
    USERNAME
    -0.06
    raction
    -0.06
     Wear
    -0.06
    _HTML
    -0.06
    quares
    -0.06
    ateř
    -0.06
    anvas
    -0.06
     rotations
    -0.06
    POSITIVE LOGITS
     보
    0.07
    ศจ
    0.07
     umožňuje
    0.07
     Tokyo
    0.07
     xét
    0.06
     Kong
    0.06
     듣
    0.06
    ám
    0.06
    },↵↵
    0.06
     Ör
    0.06
    Act Density 0.001%

    No Known Activations