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

    Neuronpedia

    INDEX
    Explanations

    modern

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     reput
    -0.07
     uploading
    -0.07
     Đó
    -0.06
     scratching
    -0.06
    turtle
    -0.06
    ┣
    -0.06
     jj
    -0.06
    něž
    -0.06
    	st
    -0.06
    POSITIVE LOGITS
    Runner
    0.06
    賣
    0.06
     Diabetes
    0.06
     rotates
    0.06
    erro
    0.06
     Machinery
    0.06
    invoices
    0.06
     Bergen
    0.06
    ...
↵
    0.06
    $conn
    0.06
    Act Density 0.001%

    No Known Activations