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

    Neuronpedia

    INDEX
    Explanations

    percentages and decimals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    》、《
    0.73
     bunches
    0.70
     Chia
    0.69
    னையும்
    0.66
     podia
    0.66
    味わ
    0.66
    ا۔
    0.65
     crítica
    0.64
     یہودیوں
    0.64
     Чу
    0.64
    POSITIVE LOGITS
    Heather
    0.82
    igle
    0.80
    XO
    0.76
    By
    0.74
    jari
    0.73
     fundraiser
    0.73
    報
    0.72
    jol
    0.70
    0.70
     yönet
    0.69
    Act Density 0.020%

    No Known Activations