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

    Neuronpedia

    INDEX
    Explanations

    updates and improvements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.91
    </h3>
    0.85
    </h2>
    0.79
    </span>
    0.71
    </h6>
    0.70
    ،
    0.69
    </b>
    0.69
    </h1>
    0.66
     fluorescent
    0.66
    </h5>
    0.66
    POSITIVE LOGITS
    a
    1.17
    n
    1.02
    z
    0.99
    is
    0.98
    on
    0.98
    ul
    0.89
    c
    0.89
    y
    0.88
    ه
    0.88
    in
    0.84
    Act Density 0.033%

    No Known Activations