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

    Neuronpedia

    INDEX
    Explanations

    tracking cookies and ads

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     PASSWORD
    0.55
     archiv
    0.49
     साइबर
    0.49
     নথি
    0.49
    アーカイブ
    0.49
     cybers
    0.47
     arşiv
    0.47
     ODBC
    0.47
     पासवर्ड
    0.46
     passwords
    0.46
    POSITIVE LOGITS
     ads
    0.45
    price
    0.40
     alternative
    0.40
    reux
    0.40
    Price
    0.39
    ly
    0.38
    icar
    0.38
     dozens
    0.38
     var
    0.38
    ons
    0.38
    Act Density 0.039%

    No Known Activations