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

    Neuronpedia

    INDEX
    Explanations

    semantic relations, categories, knowledge graphs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ф
    0.58
    FN
    0.49
    getCQL
    0.47
     یونی
    0.46
    am
    0.46
    CF
    0.45
    emal
    0.45
    ال
    0.44
    Ви
    0.44
    aml
    0.44
    POSITIVE LOGITS
     assuming
    0.44
     jawaban
    0.42
    èlement
    0.41
     wers
    0.40
     again
    0.40
    ᓕ
    0.39
    ிக்
    0.39
    意的
    0.39
    ђено
    0.38
    harmony
    0.38
    Act Density 0.000%

    No Known Activations