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

    Neuronpedia

    INDEX
    Explanations

    Separable convolutions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    L
    0.50
     memperkenalkan
    0.49
    ilize
    0.49
     October
    0.49
    people
    0.47
    সকল
    0.47
    speople
    0.47
    tional
    0.47
    x
    0.46
    ności
    0.46
    POSITIVE LOGITS
     headsets
    0.44
    冎
    0.44
    恽
    0.43
     impedances
    0.43
     pulsations
    0.43
     其
    0.42
     яичко
    0.42
    িল্প
    0.42
     gevoel
    0.42
    镙
    0.42
    Act Density 0.000%

    No Known Activations