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

    Neuronpedia

    INDEX
    Explanations

    narratives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     deportation
    -0.07
    _SHADOW
    -0.07
    lbrace
    -0.06
    创新发展
    -0.06
    .def
    -0.06
    较多
    -0.06
     früh
    -0.06
    NavigationView
    -0.06
     духов
    -0.06
     Jarvis
    -0.06
    POSITIVE LOGITS
    notated
    0.07
     getLast
    0.06
    -site
    0.06
    owed
    0.06
     (),↵
    0.06
    illing
    0.06
     Houses
    0.06
    -treated
    0.06
    濂
    0.06
    -lines
    0.06
    Act Density 0.024%

    No Known Activations