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

    Neuronpedia

    INDEX
    Explanations

    .txt

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    owl
    -0.08
     Drinks
    -0.06
     최저
    -0.06
    ierre
    -0.06
    OWL
    -0.06
    iral
    -0.06
     Teil
    -0.06
     Bryant
    -0.06
     ऐ
    -0.06
     strands
    -0.06
    POSITIVE LOGITS
    .txt
    0.09
    .cmb
    0.06
    egis
    0.06
    .rb
    0.06
     comprises
    0.06
    <int
    0.06
    (contents
    0.06
    (Mat
    0.06
    .send
    0.06
    .';↵
    0.06
    Act Density 0.002%

    No Known Activations