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

    Neuronpedia

    INDEX
    Explanations

    data types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ět
    0.48
    enumerate
    0.48
    rometer
    0.47
    ę
    0.47
    انيا
    0.47
    ógicas
    0.46
    ersonal
    0.46
    renew
    0.45
    éd
    0.45
     autrefois
    0.45
    POSITIVE LOGITS
    場の
    0.43
     UAE
    0.43
     Suburban
    0.43
     Cao
    0.43
     VFX
    0.42
    ությ
    0.42
     Bikini
    0.42
    \}\
    0.41
     keting
    0.41
    やま
    0.41
    Act Density 0.000%

    No Known Activations