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

    Neuronpedia

    INDEX
    Explanations

    time horizons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    0.47
     espectadores
    0.41
    Invoice
    0.40
     LIBRARY
    0.40
     Accreditation
    0.39
     ON
    0.39
     isOn
    0.39
     Marilyn
    0.38
     On
    0.38
     Disp
    0.38
    POSITIVE LOGITS
     facilement
    0.50
    сний
    0.49
    toys
    0.48
     подходит
    0.47
    ்துற
    0.47
     регулярно
    0.47
     време
    0.46
     к
    0.46
    时间
    0.46
    []);
    0.45
    Act Density 0.000%

    No Known Activations