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

    Neuronpedia

    INDEX
    Explanations

    sin and corruption

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     সফদর
    0.52
     सकुशल
    0.49
     serendip
    0.48
     الاكس
    0.48
     ভালোভাবে
    0.48
    屹
    0.47
     నిర్వహ
    0.47
     சுத்தம்
    0.47
    ርስዎ
    0.46
     remaster
    0.46
    POSITIVE LOGITS
     idolat
    1.33
     corrupt
    1.05
     false
    1.02
     immoral
    1.00
     impure
    0.99
     impurity
    0.95
     Satan
    0.93
     idol
    0.92
     pagan
    0.91
     الشيطان
    0.91
    Act Density 0.032%

    No Known Activations