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

    Neuronpedia

    INDEX
    Explanations

    Pol

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ickle
    -0.06
    地下
    -0.06
    ив
    -0.06
    -wide
    -0.06
    page
    -0.06
     Revolution
    -0.06
    يدي
    -0.06
     لم
    -0.06
    centers
    -0.06
     DE
    -0.06
    POSITIVE LOGITS
     slightest
    0.07
     появ
    0.07
    ")){
↵
    0.06
     tying
    0.06
    .`,↵
    0.06
    .EN
    0.06
    Successful
    0.06
     проис
    0.06
    xFA
    0.06
    ))/
    0.06
    Act Density 0.001%

    No Known Activations