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

    Neuronpedia

    INDEX
    Explanations

    smallest

    np_max-act · gemini-2.0-flash

    The neuron detects ranking or ordering terms—words that express ordinality or superlatives (e.g. “smallest,” “biggest,” “second,” “third,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     guiding
    -0.07
     backers
    -0.07
     війсь
    -0.06
    _TRY
    -0.06
    _INSTALL
    -0.06
     UID
    -0.06
    幼
    -0.06
    OURSE
    -0.06
    manual
    -0.06
    >".
    -0.06
    POSITIVE LOGITS
     податков
    0.07
    　V
    0.07
     hindsight
    0.06
     meio
    0.06
    woods
    0.06
     Streams
    0.06
    _CITY
    0.06
     conceivable
    0.06
     Máy
    0.06
     Sahara
    0.06
    Act Density 0.001%

    No Known Activations