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

    Neuronpedia

    INDEX
    Explanations

    structured lists and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     journaling
    0.77
     microbiome
    0.74
     onboarding
    0.73
     Chromebook
    0.71
     underwhelming
    0.71
    스를
    0.70
     Mindfulness
    0.67
     insights
    0.66
     mindfulness
    0.66
     impactful
    0.64
    POSITIVE LOGITS
     homens
    0.68
     تے
    0.68
    ไม่มี
    0.67
     сих
    0.66
    انہوں
    0.66
     lunghezza
    0.66
     ৮
    0.65
     obiekt
    0.65
     বর্বর
    0.65
     ciri
    0.64
    Act Density 0.004%

    No Known Activations