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

    Neuronpedia

    INDEX
    Explanations

    abbreviations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    S
    -0.78
    <bos>
    -0.69
    C
    -0.67
    D
    -0.66
    Ds
    -0.65
    T
    -0.65
     Majefty
    -0.64
     Monfieur
    -0.63
    Ps
    -0.61
    Cs
    -0.61
    POSITIVE LOGITS
    }>;
    0.68
    )))
    0.66
    }");
    0.65
    ”]
    0.65
    ]}"
    0.65
    numerusform
    0.65
    />";
    0.64
    ]`
    0.63
    ruptedException
    0.63
    ]()
    0.63
    Act Density 0.178%

    No Known Activations