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

    Neuronpedia

    INDEX
    Explanations

    technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ging
    -0.54
    j
    -0.53
    z
    -0.53
    jno
    -0.52
    ing
    -0.51
    quality
    -0.51
    i
    -0.50
    ts
    -0.50
    boring
    -0.50
    chluss
    -0.49
    POSITIVE LOGITS
    )");
    0.90
    )";
    0.87
     صوتيه
    0.85
    )"),
    0.83
    >");
    0.82
    WriteBarrier
    0.81
    Personensuche
    0.80
    tagHelperRunner
    0.79
    >');
    0.77
    }.
    0.76
    Act Density 0.486%

    No Known Activations