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

    Neuronpedia

    INDEX
    Explanations

    ultimate continuation or platform

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    滴
    0.46
    哪些
    0.45
     publi
    0.45
    șit
    0.45
     కూడా
    0.44
     producido
    0.44
    typed
    0.43
    credi
    0.43
     যেটা
    0.43
     detto
    0.43
    POSITIVE LOGITS
     Ю
    0.48
    Garden
    0.47
     Рэ
    0.45
     ANG
    0.43
    峠
    0.43
     аль
    0.42
     К
    0.42
     Аль
    0.42
     протяжении
    0.42
     Вя
    0.42
    Act Density 0.005%

    No Known Activations