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

    Neuronpedia

    INDEX
    Explanations

    opportunities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    alaria
    -0.06
    gu
    -0.06
     configFile
    -0.06
    卫
    -0.06
    ensemble
    -0.06
     Germans
    -0.06
    �
    -0.06
     ELSE
    -0.06
     chó
    -0.06
     zem
    -0.06
    POSITIVE LOGITS
    _avatar
    0.07
    Sit
    0.07
    toUpperCase
    0.07
     والت
    0.06
    �
    0.06
    čním
    0.06
     Techniques
    0.06
    娘
    0.06
    Highest
    0.06
    ");
↵
    0.06
    Act Density 0.021%

    No Known Activations