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

    Neuronpedia

    INDEX
    Explanations

    elefante, punch, electrical probe, sleep

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nhắn
    2.62
     escrito
    2.54
     dotycz
    2.51
    どもの
    2.45
    $.
    2.41
     annoy
    2.36
    gers
    2.29
    rió
    2.25
    lycer
    2.25
    ৩
    2.25
    POSITIVE LOGITS
    ية
    4.45
    ت
    4.33
    ing
    4.03
    я
    3.93
    ed
    3.83
    ة
    3.39
    ️
    3.36
    า
    3.22
    ು
    3.22
    ிய
    3.08
    Act Density 0.078%

    No Known Activations