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

    Neuronpedia

    INDEX
    Explanations

    but you the top clean Ubuntu Yes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    remos
    1.20
    なくて
    1.19
    它
    1.16
    ﺽ
    1.11
    чі
    1.11
    قد
    1.10
    Em
    1.08
     disposed
    1.08
    িও
    1.07
    它的
    1.06
    POSITIVE LOGITS
    ۰۰
    1.14
     culturais
    1.11
    mov
    1.08
     театр
    1.07
     крови
    1.06
     blow
    1.04
     booklet
    1.04
     나타
    1.03
     страна
    1.01
     meningkat
    0.99
    Act Density 0.000%

    No Known Activations