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

    Neuronpedia

    INDEX
    Explanations

    terms associated with identification and introductions

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

    names and labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -0.55
    (!__
    -0.49
    ativement
    -0.48
     allAfrica
    -0.46
    EndContext
    -0.46
    RIV
    -0.44
     CreateTagHelper
    -0.44
     entityManager
    -0.43
    MAZ
    -0.43
    CompleteListener
    -0.43
    POSITIVE LOGITS
     captions
    0.47
     anonyme
    0.43
     labeled
    0.43
     etik
    0.43
     labels
    0.43
    úblico
    0.40
    setToolTipText
    0.40
     labeling
    0.40
     pegatinas
    0.39
     curieux
    0.39
    Act Density 0.096%

    No Known Activations