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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    omon
    -0.07
    人間
    -0.06
     Speak
    -0.06
    �
    -0.06
     opponents
    -0.06
     a
    -0.06
     Blessed
    -0.06
     مردم
    -0.06
     Rot
    -0.06
    270
    -0.06
    POSITIVE LOGITS
     대구
    0.07
     الموس
    0.06
    ksiyon
    0.06
     فنی
    0.06
     exhibition
    0.06
     Kanye
    0.06
    (enum
    0.06
     Tanzania
    0.06
     strives
    0.06
     sürede
    0.05
    Act Density 0.058%

    No Known Activations