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

    Neuronpedia

    INDEX
    Explanations

    allowing others

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     फूड
    0.42
    semibold
    0.42
     photoshoot
    0.42
     भाँ
    0.41
    unsplash
    0.40
    mirea
    0.40
    ೇಳ
    0.38
    faq
    0.38
    ale
    0.38
    goers
    0.38
    POSITIVE LOGITS
     کمپیوٹر
    0.39
    （
    0.39
    Comput
    0.39
    Selon
    0.39
    ↵
    0.38
    Daten
    0.38
     komputer
    0.37
    Questa
    0.36
     Regeln
    0.36
     вычисли
    0.36
    Act Density 0.001%

    No Known Activations