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

    Neuronpedia

    INDEX
    Explanations

    side

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    코
    -0.08
    .AP
    -0.07
     variability
    -0.07
    .APP
    -0.07
     drilling
    -0.07
     resilience
    -0.07
     resil
    -0.07
    堂
    -0.07
     здоровья
    -0.07
    씩
    -0.07
    POSITIVE LOGITS
     Photographer
    0.08
    श्म
    0.08
    Matcher
    0.08
     Matcher
    0.08
     गुरु
    0.08
    ahil
    0.08
     Ethical
    0.08
    Lady
    0.08
     guilty
    0.08
     Judgment
    0.08
    Act Density 0.003%

    No Known Activations