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

    Neuronpedia

    INDEX
    Explanations

    post

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of the identifier “post” (e.g. in variable names, class names, template keys, etc.) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    lessly
    -0.07
    ------------------------------------------------
    -0.07
     tons
    -0.07
    ooled
    -0.06
     çev
    -0.06
    舗
    -0.06
    								
↵
    -0.06
    riv
    -0.06
    continued
    -0.06
    Accordion
    -0.06
    POSITIVE LOGITS
     yoktur
    0.07
     amel
    0.07
    ýval
    0.06
     Quân
    0.06
     дол
    0.06
    （笑
    0.06
     Is
    0.06
    초등학교
    0.06
    jt
    0.06
    _UPLOAD
    0.06
    Act Density 0.045%

    No Known Activations