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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash

    The neuron selectively responds to tokens that are parts of floating‐point numeric literals (decimal fractions) in technical or patent‐style text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     والم
    -0.07
    ############################################################
    -0.07
    .trailingAnchor
    -0.06
     massages
    -0.06
     kaç
    -0.06
     thật
    -0.06
     bulunan
    -0.06
     daha
    -0.06
    GMEM
    -0.06
     раздел
    -0.06
    POSITIVE LOGITS
     doctr
    0.07
     stools
    0.06
    funcs
    0.06
     oily
    0.06
     extensively
    0.06
     ΔE
    0.06
    ”。↵↵
    0.06
    (freq
    0.06
    ression
    0.06
     chill
    0.06
    Act Density 0.207%

    No Known Activations