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

    Neuronpedia

    INDEX
    Explanations

    processing and interpretation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     multiplayer
    0.71
     Joc
    0.67
     gitt
    0.67
     joc
    0.66
     rental
    0.66
     roaming
    0.65
     جواب
    0.64
     complacency
    0.64
     roulette
    0.62
     generals
    0.61
    POSITIVE LOGITS
     processing
    1.82
     Processing
    1.78
    Processing
    1.68
    processing
    1.62
     processed
    1.50
     preprocessing
    1.50
     PROCESSING
    1.47
    加工
    1.39
     प्रसंस्करण
    1.39
     filtering
    1.34
    Act Density 2.628%

    No Known Activations