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

    Neuronpedia

    INDEX
    Explanations

    single letters enclosed in parenthesis

    oai_token-act-pair · gemini-2.0-flash

    say ")"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "]));
    -0.55
     للمعارف
    -0.52
    ")));
    -0.49
    ")));
    -0.49
    ')));
    -0.49
    ]));
    -0.49
    PerformLayout
    -0.47
    )));
    -0.47
    "));
    -0.47
    WebServlet
    -0.47
    POSITIVE LOGITS
    entai
    0.68
    iable
    0.63
    omorphic
    0.62
    INCT
    0.62
    IEVE
    0.59
    otan
    0.59
    ressive
    0.59
    otonic
    0.59
    gnition
    0.58
    uite
    0.58
    Act Density 8.768%

    No Known Activations