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

    Neuronpedia

    INDEX
    Explanations

    legal and court matters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    是
    0.41
    は
    0.39
    ની
    0.38
    는
    0.36
    0.34
    lardı
    0.33
     उन्होंने
    0.33
    ländischen
    0.32
    ный
    0.31
    و
    0.31
    POSITIVE LOGITS
     a
    0.40
    ade
    0.35
    ות
    0.33
     or
    0.33
    ad
    0.32
     cravings
    0.30
     e
    0.30
    antal
    0.29
    one
    0.29
     reorgan
    0.29
    Act Density 0.054%

    No Known Activations