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

    Neuronpedia

    INDEX
    Explanations

    phrases related to gratitude and community involvement

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

    community involvement and voting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AsUp
    -0.50
    hots
    -0.47
     lenker
    -0.45
     rhestr
    -0.45
    alité
    -0.45
    InitVars
    -0.45
    Hozzáférés
    -0.43
    IndentedString
    -0.42
    GEBURTSDATUM
    -0.41
    KURZBESCHREIBUNG
    -0.41
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.47
     sauve
    0.44
    arrêter
    0.39
     fizer
    0.37
    Contribute
    0.36
    jsii
    0.36
     contribute
    0.35
    Ingredienti
    0.35
     giu
    0.35
    UseVisualStyle
    0.34
    Act Density 0.016%

    No Known Activations