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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pandemic
    -0.07
    ại
    -0.07
    invoice
    -0.06
     prvním
    -0.06
     informations
    -0.06
     Imported
    -0.06
     zum
    -0.06
     Approach
    -0.06
     Twenty
    -0.06
     이렇게
    -0.06
    POSITIVE LOGITS
    نسان
    0.07
     USA
    0.07
    (inputs
    0.06
     الميلاد
    0.06
     Anglo
    0.06
    .news
    0.06
     bp
    0.06
    .assertFalse
    0.06
    '];
↵
↵
    0.06
    ';↵
    0.06
    Act Density 0.037%

    No Known Activations