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

    Neuronpedia

    INDEX
    Explanations

    Viewpoints/perspectives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bunny
    -0.07
     bik
    -0.07
     Alicia
    -0.07
     Sierra
    -0.06
    jets
    -0.06
     rencontre
    -0.06
    -twitter
    -0.06
    汝
    -0.06
    /Delete
    -0.06
     пред
    -0.06
    POSITIVE LOGITS
    켠
    0.07
    isecond
    0.07
     }},↵
    0.07
    واق
    0.07
    赜
    0.07
    .lineTo
    0.07
    opo
    0.06
    电费
    0.06
    パイ
    0.06
    깝
    0.06
    Act Density 0.021%

    No Known Activations