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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Mastery
    0.45
    ᐉ
    0.42
     Positioning
    0.41
    コントロール
    0.41
     Controls
    0.40
    %$
    0.40
    Controls
    0.39
     നന്ന
    0.39
     Data
    0.39
     ситуации
    0.39
    POSITIVE LOGITS
     intend
    0.39
    बर्ग
    0.39
    igations
    0.38
     regimen
    0.38
    oirs
    0.37
    cznej
    0.36
     prayers
    0.36
     éclair
    0.35
    éclair
    0.35
     leased
    0.35
    Act Density 0.000%

    No Known Activations