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

    Neuronpedia

    INDEX
    Explanations

    likely to be contrasted

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     đã
    0.41
     chưa
    0.41
     αυτό
    0.37
     dostęp
    0.37
     chắn
    0.36
    syst
    0.36
     деко
    0.36
     daqu
    0.36
     bước
    0.35
     vẫn
    0.35
    POSITIVE LOGITS
    یا
    0.48
    ق
    0.35
    iological
    0.32
    cj
    0.32
    ك
    0.32
    cu
    0.31
    ipping
    0.31
    そして
    0.31
    cn
    0.31
    in
    0.30
    Act Density 0.000%

    No Known Activations