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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash

    This neuron responds to clause-separating punctuation, especially commas.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _descriptor
    -0.06
    ;
    -0.06
     دوم
    -0.06
     trolls
    -0.06
     zví
    -0.06
     That
    -0.06
    REFER
    -0.06
     ди
    -0.06
     ENGINE
    -0.06
     Cow
    -0.06
    POSITIVE LOGITS
    ,)↵
    0.06
     mysqli
    0.06
    _table
    0.06
    ,w
    0.06
    _fft
    0.06
    imony
    0.06
    *******/↵
    0.06
    elez
    0.06
     即
    0.06
    issue
    0.06
    Act Density 0.175%

    No Known Activations