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

    Neuronpedia

    INDEX
    Explanations

    new Date

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     अपराधियों
    0.40
     Thread
    0.40
     Ici
    0.38
     Default
    0.37
     Chang
    0.37
     Gor
    0.37
     নিরস্ত্র
    0.37
     Armani
    0.37
     Athletic
    0.37
     Mac
    0.36
    POSITIVE LOGITS
    ainment
    0.41
     dropout
    0.40
    ständig
    0.39
     صورة
    0.38
     이미지
    0.38
     image
    0.37
     توصل
    0.36
    úra
    0.36
    ల్లు
    0.36
    イメージ
    0.35
    Act Density 0.002%

    No Known Activations