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

    Neuronpedia

    INDEX
    Explanations

    bonus codes, features, or rounds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     selfies
    0.66
     Niko
    0.64
     θ
    0.64
     basalt
    0.63
     Shun
    0.63
     ¹
    0.62
     abortions
    0.62
     vấn
    0.62
     it
    0.61
     Merritt
    0.61
    POSITIVE LOGITS
    <0x0D>
    0.86
    </h3>
    0.63
    /
    0.61
    i
    0.57
    ي
    0.56
    د
    0.55
    </th>
    0.55
    </h1>
    0.55
    н
    0.55
    </em>
    0.55
    Act Density 0.001%

    No Known Activations