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

    Neuronpedia

    INDEX
    Explanations

    App

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Peninsula
    -0.07
     neboť
    -0.07
     outro
    -0.06
    Ram
    -0.06
    _density
    -0.06
     makeover
    -0.06
    遠
    -0.06
    Mas
    -0.06
    вих
    -0.06
     bunlar
    -0.06
    POSITIVE LOGITS
     değiş
    0.07
     �
    0.06
    /entities
    0.06
    &↵
    0.06
    >(&
    0.06
    谷
    0.06
     Об
    0.06
     میتوان
    0.06
    	↵	↵
    0.06
    ||↵
    0.06
    Act Density 0.014%

    No Known Activations