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

    Neuronpedia

    INDEX
    Explanations

    "at least" or "more than"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     continent
    -0.08
    洞
    -0.07
    ought
    -0.07
    ahkan
    -0.07
    宙
    -0.07
    .espresso
    -0.07
    bus
    -0.06
    аль
    -0.06
     Semester
    -0.06
    iết
    -0.06
    POSITIVE LOGITS
     insiders
    0.08
    _PANEL
    0.07
    _SZ
    0.07
    islation
    0.07
    .wh
    0.07
    nu
    0.07
    标签
    0.07
    究竟
    0.07
    arduino
    0.07
    LABEL
    0.07
    Act Density 0.012%

    No Known Activations