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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     swirl
    -0.08
    +[
    -0.07
    '";
↵
    -0.07
    ubuntu
    -0.06
     Folding
    -0.06
    _GOOD
    -0.06
     Sat
    -0.06
     Comes
    -0.06
     Mary
    -0.06
    .tiles
    -0.06
    POSITIVE LOGITS
    (cols
    0.07
    (annotation
    0.07
     solve
    0.06
    ursively
    0.06
     eligibility
    0.06
     forced
    0.06
    超
    0.06
     aforementioned
    0.06
    -ready
    0.06
    Jake
    0.06
    Act Density 0.000%

    No Known Activations