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

    Neuronpedia

    INDEX
    Explanations

    parts of Java code, including code blocks, comments, and method declarations

    oai_token-act-pair · gemini-2.0-flash

    source code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rendus
    -0.59
    :✨
    -0.57
    Personensuche
    -0.57
    šanās
    -0.56
     định
    -0.55
    AFFIRMED
    -0.54
    Výhody
    -0.54
    })));
    -0.54
     rápidas
    -0.52
     hâte
    -0.52
    POSITIVE LOGITS
    VersionUID
    0.53
     Mec
    0.50
     BOW
    0.48
    bcryptjs
    0.47
    WireFormatLite
    0.46
    SharedDtor
    0.46
     Apro
    0.46
    retario
    0.46
     Enumerable
    0.45
    ArrayOf
    0.44
    Act Density 1.255%

    No Known Activations