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

    Neuronpedia

    INDEX
    Explanations

    checking scripts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Rochelle
    0.47
     Phar
    0.43
    ‌ర
    0.41
     PG
    0.40
     stora
    0.39
     belirtti
    0.38
    еме
    0.38
     Yoshida
    0.38
     Hepat
    0.38
     Wembley
    0.38
    POSITIVE LOGITS
     recovered
    0.38
     теперь
    0.37
     angrily
    0.37
    曲
    0.37
    袖
    0.37
    🗞
    0.36
     ^{-
    0.36
    }}^{*
    0.36
    arcs
    0.36
     sensed
    0.35
    Act Density 0.000%

    No Known Activations