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

    Neuronpedia

    INDEX
    Explanations

    how to guides, introductory phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     spe
    0.41
     steeply
    0.40
     conceit
    0.40
     astounding
    0.39
     experimentally
    0.39
     application
    0.39
     hypothesis
    0.39
     startling
    0.39
     strikingly
    0.38
     archetype
    0.38
    POSITIVE LOGITS
     كيفية
    0.58
     Langkah
    0.50
    Finding
    0.49
    当你
    0.48
     Bagaimana
    0.48
     ඔබේ
    0.48
     bagaimana
    0.47
     عندما
    0.47
     Sabemos
    0.46
     Når
    0.45
    Act Density 0.280%

    No Known Activations