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

    Neuronpedia

    INDEX
    Explanations

    descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Which
    -0.08
    "Do
    -0.08
    /App
    -0.07
     disappointment
    -0.07
     وكان
    -0.07
    等着
    -0.07
    '),
    -0.07
    什么地方
    -0.07
    thank
    -0.07
    وضح
    -0.07
    POSITIVE LOGITS
     Careers
    0.08
    fld
    0.07
    הר
    0.07
     tr
    0.07
     다
    0.07
     Tours
    0.07
     clazz
    0.06
    삥
    0.06
     profes
    0.06
     freely
    0.06
    Act Density 0.002%

    No Known Activations