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

    Neuronpedia

    INDEX
    Explanations

    human needs and desires

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     justifyContent
    0.43
    がありました
    0.42
    就要
    0.42
    窜
    0.42
     للك
    0.41
     있다면
    0.39
     setan
    0.39
     contest
    0.38
     kerusakan
    0.38
     cheese
    0.38
    POSITIVE LOGITS
     Median
    0.45
     Zn
    0.45
    éget
    0.43
    ৌম
    0.41
    https
    0.40
    চ্ছিন্ন
    0.40
     समझने
    0.40
    Zn
    0.39
     Mitra
    0.39
     SVG
    0.39
    Act Density 0.002%

    No Known Activations