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

    Neuronpedia

    INDEX
    Explanations

    phrases related to privacy policies and user consent

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

    privacy notice, terms, agreements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.74
     esternos
    -0.65
    bootstrapcdn
    -0.60
    DockStyle
    -0.59
    tinyos
    -0.59
    ſicht
    -0.59
    aeros
    -0.59
    ⸅
    -0.58
    ſſung
    -0.58
    enterOuterAlt
    -0.58
    POSITIVE LOGITS
    Personendaten
    0.45
     ,
    0.30
     énon
    0.28
     vigencia
    0.28
     importancia
    0.28
     circonstances
    0.27
     poderão
    0.27
     cucchiaio
    0.26
     estructura
    0.26
     ifade
    0.25
    Act Density 0.009%

    No Known Activations