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

    Neuronpedia

    INDEX
    Explanations

    closing punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </code>
    0.95
    </strong>
    0.85
    ”।
    0.85
    \".
    0.81
    "।
    0.79
     nematodes
    0.78
    ";
    0.75
    >";
    0.74
     padded
    0.74
    য়াদ
    0.72
    POSITIVE LOGITS
    <h3>
    1.84
    ,)
    1.65
    ,))
    1.46
    ',)
    1.46
    .)
    1.36
    </h3>
    1.35
    。）
    1.34
    ###
    1.28
    ,),
    1.20
    .]
    1.18
    Act Density 0.084%

    No Known Activations