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

    Neuronpedia

    INDEX
    Explanations

    absolute states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    แซ
    0.71
     Dynamics
    0.70
     Updating
    0.62
    Updating
    0.61
    Dynamics
    0.60
     LayoutInflater
    0.60
     logika
    0.59
     Probleme
    0.59
    শক্ত
    0.59
    活力
    0.58
    POSITIVE LOGITS
     complete
    1.77
     Complete
    1.56
     utter
    1.54
    complete
    1.50
     total
    1.49
     absolute
    1.45
    Complete
    1.45
     totale
    1.40
     completa
    1.38
    total
    1.32
    Act Density 0.535%

    No Known Activations