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

    Neuronpedia

    INDEX
    Explanations

    guidelines and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    item
    0.42
    subset
    0.42
     levies
    0.41
    setup
    0.41
    subject
    0.41
    awah
    0.41
    where
    0.40
    hsl
    0.40
    금
    0.40
    abin
    0.39
    POSITIVE LOGITS
    庣
    0.52
     vittoria
    0.47
     giảm
    0.47
     caffè
    0.46
     bankrupt
    0.45
    یمپ
    0.45
    творення
    0.44
     sintomi
    0.44
    తున్నారు
    0.44
     fondateur
    0.44
    Act Density 0.000%

    No Known Activations