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

    Neuronpedia

    INDEX
    Explanations

    ellipses indicate continuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🆁
    1.77
    ت
    1.63
    ação
    1.48
     gesagt
    1.47
    ن
    1.47
    いた
    1.42
    azione
    1.41
     localizado
    1.40
    ič
    1.39
    ik
    1.38
    POSITIVE LOGITS
    nt
    1.67
    ים
    1.53
     siphon
    1.48
    요
    1.48
    ς
    1.45
    ள்
    1.41
    ный
    1.41
    s
    1.41
    sun
    1.38
    ss
    1.37
    Act Density 0.000%

    No Known Activations