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

    Neuronpedia

    INDEX
    Explanations

    Locations, events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ired
    -0.07
     Пот
    -0.06
    典
    -0.06
     cameo
    -0.06
    ИТ
    -0.06
     थ
    -0.06
    тии
    -0.06
     cheated
    -0.06
    …ط
    -0.05
    /problems
    -0.05
    POSITIVE LOGITS
    licenses
    0.07
    Locker
    0.07
    TabControl
    0.07
    configure
    0.07
    .Def
    0.07
    -metadata
    0.07
    306
    0.07
     спіль
    0.07
     [],↵
    0.07
    _custom
    0.07
    Act Density 0.101%

    No Known Activations