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

    Neuronpedia

    INDEX
    Explanations

    query and editor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    نيف
    0.43
    能
    0.43
     kapac
    0.41
     zelen
    0.41
    算
    0.41
    蠕
    0.41
     aktiv
    0.40
    емости
    0.40
     kult
    0.40
     dekor
    0.40
    POSITIVE LOGITS
     interrogated
    0.46
    になっている
    0.44
     알려
    0.44
     επίσης
    0.44
     έχουν
    0.43
    ।--
    0.43
     procédures
    0.43
     Hindi
    0.41
    ။
    0.41
     결과를
    0.41
    Act Density 0.010%

    No Known Activations