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

    Neuronpedia

    INDEX
    Explanations

    sorting code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .def
    -0.06
     ⟨
    -0.06
    łe
    -0.06
     صن
    -0.06
    ็ต
    -0.06
    intl
    -0.06
     gameObject
    -0.06
    closure
    -0.06
     Handling
    -0.06
     Aff
    -0.06
    POSITIVE LOGITS
     messing
    0.07
    /routes
    0.07
    What
    0.07
    ясь
    0.07
     WHAT
    0.06
     ez
    0.06
    第一次
    0.06
    (Http
    0.06
    Δεν
    0.06
     mám
    0.06
    Act Density 0.041%

    No Known Activations