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

    Neuronpedia

    INDEX
    Explanations

    Directions and image processing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	InputStream
    -0.07
    .gpu
    -0.07
    .learn
    -0.07
    .footer
    -0.06
    pivot
    -0.06
     weaker
    -0.06
    яти
    -0.06
     newPassword
    -0.06
     Dog
    -0.06
     vend
    -0.06
    POSITIVE LOGITS
     Soph
    0.06
     разных
    0.06
    ेय
    0.06
    estation
    0.06
    cash
    0.05
    ServiceImpl
    0.05
    �
    0.05
    UNITY
    0.05
     ilişk
    0.05
     posed
    0.05
    Act Density 0.121%

    No Known Activations