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

    Neuronpedia

    INDEX
    Explanations

    complex issues or sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mejor
    0.49
     melhor
    0.48
     strategies
    0.45
     mejores
    0.44
     forti
    0.44
    ચે
    0.43
     CSF
    0.43
     com
    0.43
     entornos
    0.43
     CSI
    0.43
    POSITIVE LOGITS
    튿
    0.50
    有限
    0.47
    일
    0.45
    มัน
    0.44
    {
    0.43
    会自动
    0.41
    ดำ
    0.41
    멤버
    0.41
    市内
    0.40
     hurtful
    0.40
    Act Density 0.001%

    No Known Activations