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

    Neuronpedia

    INDEX
    Explanations

    fees paid

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Has
    1.02
    was
    0.97
     చేస్తుంది
    0.88
     Has
    0.87
     was
    0.85
    Was
    0.84
     করেছিল
    0.82
    పడుతుంది
    0.81
     பாதிக்கிறது
    0.81
     বলেছিল
    0.81
    POSITIVE LOGITS
     are
    3.24
     aren
    2.85
     jsou
    2.77
     ovat
    2.76
     đều
    2.56
     são
    2.55
     vengono
    2.51
     nejsou
    2.51
     هستند
    2.47
     were
    2.47
    Act Density 0.430%

    No Known Activations