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

    Neuronpedia

    INDEX
    Explanations

    otters hold hands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     एवरी
    0.49
    ன
    0.47
     আলাই
    0.46
     Allemagne
    0.46
    neſs
    0.45
    ról
    0.45
    enburg
    0.44
    ाह
    0.43
     Já
    0.43
    ने
    0.43
    POSITIVE LOGITS
     importance
    0.56
     if
    0.48
     }
    0.48
     day
    0.47
     increases
    0.46
     chia
    0.45
     benefits
    0.45
    重視
    0.45
     earnings
    0.44
     dividends
    0.44
    Act Density 0.001%

    No Known Activations