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

    Neuronpedia

    INDEX
    Explanations

    medical advice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    आईओएस
    0.38
     treacherous
    0.37
     petrochemical
    0.37
    போக்கு
    0.37
    wärt
    0.37
    ව්
    0.36
     lacked
    0.36
     மேம்ப
    0.36
     χρόνια
    0.35
     giấc
    0.35
    POSITIVE LOGITS
    ния
    0.37
    alto
    0.37
    aaa
    0.37
     формы
    0.36
    ya
    0.35
    a
    0.35
     infall
    0.34
    диви
    0.34
     turut
    0.34
    А
    0.34
    Act Density 0.020%

    No Known Activations