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

    Neuronpedia

    INDEX
    Explanations

    inherit, inheritance, and inherited concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     obiettivi
    0.45
     සෑම
    0.41
     отдельных
    0.41
     себе
    0.40
     piacere
    0.40
     gehört
    0.40
     Peaks
    0.40
     отде
    0.39
    গেট
    0.39
     Hundreds
    0.39
    POSITIVE LOGITS
     inherit
    0.60
     насле
    0.55
    ently
    0.54
     inheriting
    0.52
    inherit
    0.50
    Inher
    0.50
     Inher
    0.47
     inheritance
    0.47
    継
    0.46
    遗产
    0.45
    Act Density 0.010%

    No Known Activations