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

    Neuronpedia

    INDEX
    Explanations

    semicolon-delimited CSVs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lepas
    0.46
    ation
    0.46
     capire
    0.44
     profit
    0.42
     menacing
    0.42
     Orwell
    0.42
     en
    0.42
     unjust
    0.41
     seorang
    0.41
     preciso
    0.41
    POSITIVE LOGITS
    િજા
    0.53
    Event
    0.52
     LDH
    0.47
     каттоо
    0.45
    Programs
    0.45
    ６
    0.44
    6
    0.44
     основных
    0.44
    均为
    0.44
    Students
    0.43
    Act Density 0.003%

    No Known Activations