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

    Neuronpedia

    INDEX
    Explanations

    first to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     especificamente
    -0.08
     अर्क
    -0.08
    عداد
    -0.08
    anei
    -0.07
     belts
    -0.07
     Apple's
    -0.07
     numer
    -0.07
     distributors
    -0.07
     indulg
    -0.07
    בורה
    -0.07
    POSITIVE LOGITS
    填写
    0.10
     encouraged
    0.09
     참여
    0.08
    PROFILE
    0.08
     encouraging
    0.08
     editable
    0.08
    เต็ม
    0.08
    /register
    0.08
     encourage
    0.08
    community
    0.08
    Act Density 0.038%

    No Known Activations