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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .ones
    -0.07
    Տ
    -0.07
    氤
    -0.07
    一流
    -0.06
    白糖
    -0.06
    㤘
    -0.06
    🌩
    -0.06
    �
    -0.06
    thumbs
    -0.06
    蓍
    -0.06
    POSITIVE LOGITS
     recently
    0.07
    年来
    0.07
    neas
    0.06
    /m
    0.06
     Practices
    0.06
    かい
    0.06
    ница
    0.06
    結果
    0.06
     Hungary
    0.06
    日后
    0.06
    Act Density 0.017%

    No Known Activations