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

    Neuronpedia

    INDEX
    Explanations

    `run` command, `netron` viewer, `PO` variations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    al
    1.49
    ↵
    1.41
    ↵↵
    1.40
    ى
    1.22
    </h3>
    1.09
    ↵↵↵
    1.06
    </th>
    1.04
    </h1>
    1.03
    ่า
    1.03
     ,
    1.02
    POSITIVE LOGITS
     anál
    1.16
    {
    1.11
    러
    1.10
    ګ
    1.07
    ਰ
    1.04
    ﾙ
    1.04
    <unused2140>
    1.04
    1.03
    ಗರ
    1.02
    ление
    1.00
    Act Density 0.000%

    No Known Activations