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

    Neuronpedia

    INDEX
    Explanations

    div

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zde
    -0.07
     paw
    -0.06
    spe
    -0.06
    ервые
    -0.06
    ked
    -0.06
    -0.06
     رم
    -0.06
    iameter
    -0.06
    maze
    -0.06
     saw
    -0.06
    POSITIVE LOGITS
     chod
    0.07
    >N
    0.07
     Emerging
    0.06
    　j
    0.06
    ительные
    0.06
     انتقال
    0.06
     screenplay
    0.06
     sharedInstance
    0.06
    дет
    0.06
     beurette
    0.06
    Act Density 0.009%

    No Known Activations