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

    Neuronpedia

    INDEX
    Explanations

    Greek dramatists and Augustine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ла
    0.82
    ł
    0.75
    ě
    0.75
    ра
    0.73
    ре
    0.60
     성장
    0.60
     pedibusque
    0.57
    re
    0.56
    ð
    0.56
    氣
    0.53
    POSITIVE LOGITS
    ق
    0.71
    nM
    0.66
    D
    0.64
    H
    0.64
     Vail
    0.64
     Moc
    0.62
     libre
    0.61
     Libre
    0.61
    ر
    0.61
    nW
    0.60
    Act Density 0.000%

    No Known Activations