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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate inclusion or examples

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    introducing lists or examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (&
    -0.40
    ViewBag
    -0.39
    [%
    -0.38
     conflit
    -0.37
    multicolumn
    -0.37
     kohdetta
    -0.37
    JV
    -0.37
    VAS
    -0.36
    ffen
    -0.35
    !=-
    -0.35
    POSITIVE LOGITS
    UnsafeEnabled
    0.47
    Datuak
    0.47
     Chwiliwch
    0.47
    ftagPool
    0.47
    üyada
    0.45
     propOrder
    0.44
    __*/
    0.44
    .*")]
    0.44
     intStringLen
    0.43
    WebVitals
    0.42
    Act Density 0.061%

    No Known Activations