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

    Neuronpedia

    INDEX
    Explanations

    Article/blog post

    np_max-act · gemini-2.0-flash

    The neuron fires on section‐heading or list‐intro nouns (e.g. “techniques,” “features,” “strategies”) that label or introduce bullet‐point lists.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     craft
    -0.07
    000
    -0.07
    -changing
    -0.07
    -sensitive
    -0.06
    -oriented
    -0.06
     generations
    -0.06
    GetCurrent
    -0.06
     deleted
    -0.06
    .getEnd
    -0.06
     employment
    -0.06
    POSITIVE LOGITS
    _bl
    0.07
    @mail
    0.07
    0.07
    _TMP
    0.06
    （笑
    0.06
     polov
    0.06
    AJ
    0.06
     mpl
    0.06
    setScale
    0.06
     EEPROM
    0.06
    Act Density 0.077%

    No Known Activations