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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating gratitude and acknowledgments

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

    declare no conflict

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Roskov
    -0.44
    lebnis
    -0.41
    GEBURTSDATUM
    -0.40
    AddTagHelper
    -0.34
    
    -0.33
    量
    -0.33
    eff
    -0.32
    restart
    -0.31
    Activité
    -0.31
    @+
    -0.30
    POSITIVE LOGITS
     family
    0.65
    family
    0.63
     família
    0.63
    Family
    0.61
     Family
    0.60
    bootstrapcdn
    0.59
     rodz
    0.58
     család
    0.58
     keluarganya
    0.58
     keluarga
    0.57
    Act Density 0.006%

    No Known Activations