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

    Neuronpedia

    INDEX
    Explanations

    finding patterns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    َ
    0.49
     salah
    0.49
    henti
    0.49
    usive
    0.49
     revamped
    0.48
    عت
    0.47
    ងារ
    0.47
     penuh
    0.47
     miserable
    0.47
     blockbuster
    0.46
    POSITIVE LOGITS
     выяв
    0.62
     속에
    0.59
     trên
    0.56
     joka
    0.55
     обнаружи
    0.55
     which
    0.54
    evident
    0.52
     결과를
    0.52
     meydana
    0.51
    Trên
    0.50
    Act Density 0.006%

    No Known Activations