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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     lightness
    1.01
     dönüş
    1.00
    ll
    0.96
     equalizer
    0.94
    𝚅
    0.93
     entr
    0.92
    toc
    0.91
    ंसर
    0.91
    to
    0.91
    格
    0.91
    POSITIVE LOGITS
    ة
    1.60
    िक
    1.34
    িত
    1.33
     পারা
    1.24
    ️
    1.23
     dogma
    1.22
    гно
    1.21
     služby
    1.20
    ed
    1.20
    ва
    1.19
    Act Density 0.000%

    No Known Activations