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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    𝙮
    2.79
    urz
    2.69
    acritic
    2.54
    𝙡
    2.52
    蟆
    2.49
    𝙚
    2.45
     ["[
    2.44
    檛
    2.37
    ंबर्स
    2.37
     coseno
    2.35
    POSITIVE LOGITS
    line
    2.26
    monium
    2.20
    net
    2.06
    nya
    1.95
    맞
    1.94
    <blockquote>
    1.91
    军
    1.90
    ly
    1.90
    lines
    1.88
    ra
    1.88
    Act Density 0.022%

    No Known Activations