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

    Neuronpedia

    INDEX
    Explanations

    conclusions or results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     paio
    0.92
     varietà
    0.85
     öffentlich
    0.84
     qualche
    0.84
     personalmente
    0.82
     variété
    0.82
     benessere
    0.81
     consigli
    0.79
     particolarmente
    0.78
     buona
    0.78
    POSITIVE LOGITS
    Therefore
    1.89
     Therefore
    1.82
    Thus
    1.59
     Thus
    1.52
    So
    1.52
    therefore
    1.49
     So
    1.43
     therefore
    1.36
     Hence
    1.34
     Consequently
    1.33
    Act Density 0.833%

    No Known Activations