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

    Neuronpedia

    INDEX
    Explanations

    object

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ersen
    -0.07
    firefox
    -0.07
     sublic
    -0.06
     подв
    -0.06
    aussian
    -0.06
    ерше
    -0.06
     aggregated
    -0.06
    _heading
    -0.06
    俄
    -0.06
     validators
    -0.06
    POSITIVE LOGITS
    Ơ
    0.06
    使用
    0.06
    FileSystem
    0.06
     stringByAppending
    0.06
     κό
    0.06
    _Frame
    0.06
    (environment
    0.06
     hardness
    0.06
    -room
    0.06
     BrowserRouter
    0.06
    Act Density 0.042%

    No Known Activations