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

    Neuronpedia

    INDEX
    Explanations

    open weights model

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ል።
    0.39
     』
    0.39
     chale
    0.39
    Projekt
    0.38
    Sele
    0.38
    븅
    0.38
    hereafter
    0.37
    ა
    0.36
    다
    0.36
     jour
    0.36
    POSITIVE LOGITS
     আকৃষ্ট
    0.43
     of
    0.43
    ஷ
    0.40
     הט
    0.40
     difícil
    0.37
     των
    0.37
     passado
    0.37
     மேற்கொள்ள
    0.37
     மட்டுமே
    0.37
     лучших
    0.37
    Act Density 0.363%

    No Known Activations