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

    Neuronpedia

    INDEX
    Explanations

    helps you find or feel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    토
    0.45
     utilizados
    0.43
     usado
    0.42
     endeav
    0.42
     Зак
    0.42
     aplicativo
    0.41
    Зак
    0.41
    사용
    0.41
    opr
    0.41
     pagamento
    0.41
    POSITIVE LOGITS
     avoid
    0.57
     avoids
    0.54
     избежать
    0.50
     achieve
    0.47
     discover
    0.46
     quench
    0.43
    éviter
    0.43
    gi
    0.43
     gain
    0.43
    rel
    0.41
    Act Density 0.002%

    No Known Activations