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

    Neuronpedia

    INDEX
    Explanations

    What IS UP?!

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Abroad
    0.43
    Sab
    0.40
    Living
    0.39
    Rein
    0.39
    Multimedia
    0.38
     Informationen
    0.38
    naissance
    0.38
    Dé
    0.37
     المز
    0.37
    extras
    0.37
    POSITIVE LOGITS
    !")
    0.40
    !!)
    0.38
    主流
    0.38
    gendes
    0.37
     decay
    0.37
    作曲
    0.37
    ！！
    0.37
    !!");
    0.36
    !')
    0.35
     early
    0.35
    Act Density 0.003%

    No Known Activations