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

    Neuronpedia

    INDEX
    Explanations

    ö, gö, tö, hö, dö starts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ًا
    0.97
     bóng
    0.86
     fullest
    0.85
    க்கொள்ள
    0.80
    로
    0.80
     reductive
    0.76
     strenuous
    0.76
     hadron
    0.76
    arange
    0.73
     الَّ
    0.73
    POSITIVE LOGITS
    ningen
    1.11
    ntgen
    1.11
    nder
    1.06
    sels
    1.05
    dagog
    1.04
    lichkeiten
    1.04
    gypt
    1.03
    sentation
    1.02
    glich
    1.01
    !\!\
    1.01
    Act Density 0.009%

    No Known Activations