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

    Neuronpedia

    INDEX
    Explanations

    numerical data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     loads
    -0.08
     Bon
    -0.07
    	reader
    -0.07
     viewers
    -0.07
    ply
    -0.07
    @Bean
    -0.07
     load
    -0.07
     posters
    -0.07
    创
    -0.06
    _DS
    -0.06
    POSITIVE LOGITS
    ']=$
    0.08
     جدا
    0.07
     Alphabet
    0.06
    �
    0.06
    ата
    0.06
    _SANITIZE
    0.06
    ่อง
    0.06
    setState
    0.06
    597
    0.06
     bunk
    0.06
    Act Density 0.157%

    No Known Activations