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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and positive sentiment

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

    recommendations and opinions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     OMITBAD
    -0.51
    Personendaten
    -0.50
    HideFlags
    -0.49
    EndContext
    -0.47
    adaptiveStyles
    -0.45
    parsedMessage
    -0.44
    ulemon
    -0.43
    createTextNode
    -0.43
    '},
    -0.41
    ',
    -0.41
    POSITIVE LOGITS
     réessayer
    0.40
    calça
    0.39
    parametrize
    0.39
     Lovato
    0.38
    PhysRevD
    0.38
    못
    0.37
    magitan
    0.37
    SqlClient
    0.36
     flamme
    0.36
    thode
    0.36
    Act Density 0.006%

    No Known Activations