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

    Neuronpedia

    INDEX
    Explanations

    code configuration files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Flip
    -0.08
    ัส
    -0.07
     nuevas
    -0.07
    -fast
    -0.07
     Ecc
    -0.07
     kitten
    -0.07
     Memory
    -0.07
     соответ
    -0.06
    แทน
    -0.06
     Tester
    -0.06
    POSITIVE LOGITS
    제
    0.07
     *))
    0.07
    cz
    0.07
     liệu
    0.07
    ょう
    0.06
    cle
    0.06
    ))
    0.06
    phas
    0.06
    发现自己
    0.06
     kel
    0.06
    Act Density 0.037%

    No Known Activations