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

    Neuronpedia

    INDEX
    Explanations

    defining purpose or aim

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aspirations
    0.40
    一句
    0.39
    dreams
    0.38
    に関
    0.38
     संवै
    0.38
     ಸಲ್ಲ
    0.38
    Dreams
    0.37
     важное
    0.37
    сное
    0.37
     శక్తి
    0.37
    POSITIVE LOGITS
     beim
    0.46
    aat
    0.44
     siis
    0.44
     installieren
    0.44
     exaggerate
    0.42
     było
    0.41
     roughly
    0.41
     deze
    0.41
     höch
    0.41
     tych
    0.41
    Act Density 0.003%

    No Known Activations