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

    Neuronpedia

    INDEX
    Explanations

    s

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     интер
    -0.07
     основе
    -0.07
     influences
    -0.06
     Terminal
    -0.06
    .weights
    -0.06
     прест
    -0.06
    coupon
    -0.06
    ині
    -0.06
     terminals
    -0.06
    .*;
↵
↵
    -0.06
    POSITIVE LOGITS
     [])↵
    0.06
    LOS
    0.06
    Formatted
    0.06
    cisi
    0.06
     happen
    0.06
     ]↵↵↵
    0.06
     %[
    0.06
    bler
    0.06
     ''
↵
    0.06
    #${
    0.06
    Act Density 0.000%

    No Known Activations