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

    Neuronpedia

    INDEX
    Explanations

    processes and steps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ный
    0.49
    س
    0.48
    ні
    0.47
    σουμε
    0.47
    го
    0.47
     அடையாள
    0.46
    û
    0.46
    нской
    0.45
    গ্রস্ত
    0.44
    м
    0.43
    POSITIVE LOGITS
     of
    0.62
    Ти
    0.54
    /
    0.54
    )
    0.52
     that
    0.52
     venues
    0.52
    (
    0.51
     formulas
    0.51
     paradigms
    0.50
    -
    0.49
    Act Density 0.000%

    No Known Activations