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

    Neuronpedia

    INDEX
    Explanations

    process information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     performer
    0.51
    kaa
    0.45
     timeframe
    0.44
     Monaco
    0.44
     region
    0.43
     delta
    0.42
     work
    0.42
    nik
    0.41
     timeline
    0.41
     எண்
    0.40
    POSITIVE LOGITS
     escánd
    0.51
    どのように
    0.50
     escultura
    0.48
     difíciles
    0.47
     ristor
    0.46
     প্রাকৃতিক
    0.46
     controvers
    0.46
    ր
    0.46
     गेम्स
    0.45
     ristrutt
    0.45
    Act Density 0.004%

    No Known Activations