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

    Neuronpedia

    INDEX
    Explanations

    democratic donor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BackgroundTask
    0.40
     resid
    0.39
    StreetMap
    0.37
    Interior
    0.37
    Figure
    0.37
    Dancing
    0.36
    Property
    0.36
     մի
    0.36
     محد
    0.36
     거
    0.35
    POSITIVE LOGITS
     eggs
    0.43
     служба
    0.42
     Eggs
    0.42
     фир
    0.41
    化した
    0.38
    eggs
    0.38
     pea
    0.38
     getattr
    0.37
    zes
    0.36
     kendine
    0.36
    Act Density 0.056%

    No Known Activations