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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash

    The neuron responds to numeric tokens that look like floating‐point literals (decimal numbers with multiple digits after the point).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    elements related to software coding concepts and elements in programming.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     unfit
    -0.07
    ัตถ
    -0.06
    STAT
    -0.06
    солют
    -0.06
     �
    -0.06
    ータ
    -0.06
    istogram
    -0.06
     मदद
    -0.06
    alamat
    -0.06
    ροχή
    -0.06
    POSITIVE LOGITS
     움직
    0.08
     certain
    0.06
     <*
    0.06
     εισ
    0.06
     지
    0.06
     HOW
    0.06
     proficiency
    0.06
     elle
    0.06
     उत
    0.06
     Merry
    0.06
    Act Density 0.000%

    No Known Activations