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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lesions
    -0.08
     oneself
    -0.06
    Je
    -0.06
     ﾊ
    -0.06
    lexible
    -0.06
     LD
    -0.06
    arded
    -0.06
     shameful
    -0.06
    以来
    -0.06
     jetzt
    -0.06
    POSITIVE LOGITS
    click
    0.07
    .HCM
    0.07
    .makeText
    0.06
    imest
    0.06
    -hook
    0.06
    .GetMapping
    0.06
    .inflate
    0.06
     центра
    0.06
    	username
    0.06
    ικά
    0.06
    Act Density 0.163%

    No Known Activations