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

    Neuronpedia

    INDEX
    Explanations

    both

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shelves
    -0.08
    coach
    -0.07
    忙
    -0.06
     refuge
    -0.06
    mite
    -0.06
     fury
    -0.06
     enhancement
    -0.06
    рек
    -0.06
    روع
    -0.06
    �인
    -0.06
    POSITIVE LOGITS
    Основ
    0.06
     Erot
    0.06
    }]↵
    0.06
    @Slf
    0.06
    	os
    0.06
     oportun
    0.06
    .iloc
    0.06
    (metrics
    0.06
    askell
    0.06
     投稿日
    0.06
    Act Density 0.000%

    No Known Activations