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

    Neuronpedia

    INDEX
    Explanations

    Code, programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     masked
    -0.07
    esterday
    -0.06
    ालय
    -0.06
    ront
    -0.06
    işleri
    -0.06
    <Task
    -0.06
     vše
    -0.06
    ranking
    -0.06
    Financial
    -0.06
     öl
    -0.06
    POSITIVE LOGITS
     кип
    0.08
    "));
↵
    0.07
     نرم
    0.06
    167
    0.06
     Müş
    0.06
    (up
    0.06
     exec
    0.06
     FileSystem
    0.06
    	word
    0.06
     αρ
    0.06
    Act Density 0.000%

    No Known Activations