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

    Neuronpedia

    INDEX
    Explanations

    actions or statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ин
    0.42
    au
    0.42
     plush
    0.42
    skih
    0.42
    ouvoir
    0.41
    atik
    0.41
    อัน
    0.40
     bespoke
    0.39
    owy
    0.39
     penchant
    0.39
    POSITIVE LOGITS
     Instead
    0.58
     Theft
    0.51
     Internship
    0.47
     defraud
    0.47
     Ignoring
    0.46
     Subtract
    0.45
     Indicator
    0.44
     ERA
    0.43
     incarceration
    0.43
     Emission
    0.42
    Act Density 0.001%

    No Known Activations