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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    //{{
    -0.08
    requ
    -0.07
    care
    -0.07
    fair
    -0.07
    ινή
    -0.06
    อต
    -0.06
    vou
    -0.06
     fw
    -0.06
    _lazy
    -0.06
    <dd
    -0.06
    POSITIVE LOGITS
     Homework
    0.07
    خي
    0.06
     tượng
    0.06
    ै?
    0.06
     GTX
    0.06
     Leave
    0.06
    sku
    0.06
     okhttp
    0.06
     Parti
    0.06
    ladesh
    0.06
    Act Density 0.000%

    No Known Activations