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

    Neuronpedia

    INDEX
    Explanations

    spoilers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    聯系
    -0.09
    人与
    -0.08
    .sock
    -0.08
     millis
    -0.08
     Qualcomm
    -0.08
     contactos
    -0.08
    :Register
    -0.08
     competencies
    -0.08
    .recycle
    -0.08
    _contacts
    -0.08
    POSITIVE LOGITS
     spoilers
    0.14
     spoiler
    0.12
    Warning
    0.10
     warnings
    0.10
    剧情
    0.09
     сюжет
    0.08
     предупреж
    0.08
     Warning
    0.08
     Disclosure
    0.08
     spoiled
    0.08
    Act Density 0.027%

    No Known Activations