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

    Neuronpedia

    INDEX
    Explanations

    "I'm"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dort
    0.39
     nebude
    0.37
    ುವುದಿಲ್ಲ
    0.37
     hamburg
    0.37
    仅
    0.37
     Zurich
    0.37
    ﺫ
    0.36
    Closest
    0.36
     allí
    0.35
     Sydney
    0.35
    POSITIVE LOGITS
     Bol
    0.40
     UserController
    0.39
    你需要
    0.39
    Bol
    0.37
    欢乐
    0.37
    ฐาน
    0.37
     Wanna
    0.36
    閪
    0.36
     Biotechnol
    0.36
    chyma
    0.35
    Act Density 0.005%

    No Known Activations