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

    Neuronpedia

    INDEX
    Explanations

    structured text formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     worry
    0.41
     policy
    0.39
    ww
    0.38
     referencing
    0.38
     author
    0.37
     inherited
    0.37
     outages
    0.37
     WWII
    0.36
     upl
    0.35
    ovanja
    0.35
    POSITIVE LOGITS
    Dependent
    0.42
    聪
    0.42
     عندك
    0.41
     الجرس
    0.40
     Dependent
    0.38
    炳
    0.38
    弦
    0.37
     عندي
    0.37
    Insertion
    0.36
     طرق
    0.35
    Act Density 0.000%

    No Known Activations