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

    Neuronpedia

    INDEX
    Explanations

    text formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     verpflicht
    0.53
    حي
    0.49
    ي
    0.48
     mantras
    0.47
    ortium
    0.43
    اني
    0.42
    libro
    0.42
    مام
    0.42
     dissent
    0.41
    givers
    0.41
    POSITIVE LOGITS
    5
    0.48
     Slot
    0.47
     Shutdown
    0.45
    akanan
    0.44
     (
    0.43
     Met
    0.43
     Size
    0.42
     Conduit
    0.42
    6
    0.42
     Smoking
    0.42
    Act Density 0.001%

    No Known Activations