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

    Neuronpedia

    INDEX
    Explanations

    descriptions of code and objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     आरती
    0.47
    ྜ
    0.41
     ajustable
    0.40
    mixing
    0.38
    ໋
    0.37
     இலவச
    0.37
     adaptador
    0.37
    瘩
    0.37
     disfr
    0.37
    ায়ণের
    0.36
    POSITIVE LOGITS
     envis
    0.47
    jej
    0.43
    lu
    0.39
     മല
    0.39
     সফরে
    0.39
     성
    0.38
     Straßen
    0.38
     Tycho
    0.38
     Mers
    0.38
    街
    0.38
    Act Density 0.000%

    No Known Activations