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

    Neuronpedia

    INDEX
    Explanations

    the ultimate question of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     बिंदु
    0.58
     द्वारा
    0.56
    emorrh
    0.56
     टिका
    0.56
    ἢ
    0.56
    ganggu
    0.55
     कक्षा
    0.55
    بھی
    0.55
     विकल्पों
    0.55
     長
    0.54
    POSITIVE LOGITS
    ال
    0.51
     cars
    0.48
    ↵↵
    0.48
     custom
    0.48
    يمان
    0.48
     p
    0.47
    ide
    0.47
     hrs
    0.46
     casamento
    0.46
     r
    0.46
    Act Density 0.000%

    No Known Activations