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

    Neuronpedia

    INDEX
    Explanations

    maximizing other options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    нтов
    0.50
    之事
    0.48
     национа
    0.48
     세계
    0.48
    に向け
    0.47
     राजनीतिक
    0.47
     нацыяна
    0.46
     سیاسی
    0.46
     полити
    0.46
     discurso
    0.46
    POSITIVE LOGITS
    di
    0.50
     risk
    0.47
    dim
    0.43
    de
    0.43
    li
    0.43
    in
    0.42
     benefit
    0.42
     berk
    0.42
    dip
    0.42
     bö
    0.41
    Act Density 0.001%

    No Known Activations