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

    Neuronpedia

    INDEX
    Explanations

    comments and optional explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     firstly
    0.38
    //
    0.38
    Firstly
    0.37
     emergent
    0.36
    まずは
    0.35
    Drum
    0.34
    均
    0.33
     تط
    0.32
    一方面
    0.32
    Karl
    0.32
    POSITIVE LOGITS
     Puedes
    0.64
     možete
    0.59
     Uncomment
    0.57
     Optionally
    0.57
     ඔබට
    0.57
    below
    0.57
    你可以
    0.56
     아래
    0.55
     możesz
    0.55
     ניתן
    0.54
    Act Density 0.006%

    No Known Activations