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

    Neuronpedia

    INDEX
    Explanations

    say symbol comments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    vič
    -0.06
     posX
    -0.06
    490
    -0.06
     />";↵
    -0.06
    
    -0.06
    ikt
    -0.06
    avě
    -0.06
     theater
    -0.06
    Limits
    -0.06
    Streams
    -0.06
    POSITIVE LOGITS
     شه
    0.07
     �
    0.07
     수강
    0.06
     Ath
    0.06
    避
    0.06
     TOD
    0.06
    娘
    0.06
    lege
    0.06
    .HttpSession
    0.06
     Мари
    0.06
    Act Density 0.014%

    No Known Activations