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

    Neuronpedia

    INDEX
    Explanations

    positive descriptors that highlight quality or affection

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

    preceding "of" or followed by "in"

    np_acts-logits-general · gemini-2.0-flash

    greatest of all time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disambiguazione
    -0.94
    makeConstraints
    -0.82
     onOptions
    -0.81
     Meksiku
    -0.77
    InjectAttribute
    -0.74
    WebElementEntity
    -0.73
    లాలు
    -0.68
    IUrlHelper
    -0.65
    évaluateur
    -0.65
     AMT
    -0.65
    POSITIVE LOGITS
     ever
    2.06
     EVER
    1.58
    ever
    1.55
     Ever
    1.46
    Ever
    1.42
     imaginable
    1.25
    EVER
    1.24
     possible
    0.99
     jamás
    0.93
     ooit
    0.92
    Act Density 0.239%

    No Known Activations