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

    Neuronpedia

    INDEX
    Explanations

    standards (

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    沬
    0.39
     вернуть
    0.38
    ரக
    0.38
     retour
    0.36
    প্রকাশ
    0.36
    لبوم
    0.36
    ]]=
    0.36
    モー
    0.35
     book
    0.35
     estás
    0.35
    POSITIVE LOGITS
     گے
    0.39
    ⑶
    0.38
     progressed
    0.37
    unable
    0.37
     accustomed
    0.36
    位
    0.36
     dispensed
    0.36
    댑
    0.36
     reliant
    0.36
    alibaba
    0.36
    Act Density 0.000%

    No Known Activations