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

    Neuronpedia

    INDEX
    Explanations

    exploring water with confidence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     infusion
    0.55
     уены
    0.51
    portal
    0.50
     полу
    0.50
     infusions
    0.50
    ise
    0.49
    villa
    0.49
     herramient
    0.48
    item
    0.48
     занятия
    0.48
    POSITIVE LOGITS
     Commission
    0.48
    يني
    0.48
    ²,
    0.43
    lerdir
    0.41
    shaus
    0.40
    奈
    0.40
    œ
    0.40
    thar
    0.39
     careful
    0.39
    蔡
    0.39
    Act Density 0.002%

    No Known Activations