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

    Neuronpedia

    INDEX
    Explanations

    say "loid ending"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     повідом
    -0.07
     popping
    -0.06
     your
    -0.06
     zaměř
    -0.06
    Hour
    -0.06
     Memories
    -0.06
     interrog
    -0.06
     UserService
    -0.06
     Your
    -0.06
    prising
    -0.06
    POSITIVE LOGITS
     Tibet
    0.08
    .nome
    0.07
    sem
    0.07
     î
    0.07
    _SPLIT
    0.07
     fel
    0.07
     absence
    0.07
     °
    0.07
    )))))↵
    0.07
    .menu
    0.06
    Act Density 0.004%

    No Known Activations