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

    Neuronpedia

    INDEX
    Explanations

    silver jewelry and accessories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    و
    0.86
    ો
    0.69
     numerator
    0.69
    ─
    0.67
    -\
    0.67
    DAYS
    0.63
     humaine
    0.63
     spus
    0.63
     suç
    0.63
    xor
    0.62
    POSITIVE LOGITS
    𝐞
    0.89
     ported
    0.76
    <0xDB>
    0.75
    rawing
    0.74
    𝐢
    0.73
    𝐣
    0.73
    𝐬
    0.72
    𝐪
    0.72
     leptons
    0.71
    𝐧
    0.71
    Act Density 0.169%

    No Known Activations