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

    Neuronpedia

    INDEX
    Explanations

    best

    np_max-act · gemini-2.0-flash

    The neuron detects superlative adjectives (words with an “-est” ending).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    rich
    -0.07
    इन
    -0.06
    79
    -0.06
     дев
    -0.06
     θα
    -0.06
     builds
    -0.06
     AFTER
    -0.06
     четвер
    -0.06
     tolerance
    -0.06
     fri
    -0.06
    POSITIVE LOGITS
     Shortcut
    0.07
    reatest
    0.07
     //////////////////////////////////////////////////////////////////////////
    0.06
     قهر
    0.06
     toddlers
    0.06
     나라
    0.06
     rooft
    0.06
    .TextEdit
    0.06
    .contentMode
    0.06
    _Position
    0.06
    Act Density 0.038%

    No Known Activations