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

    Neuronpedia

    INDEX
    Explanations

    a bit more

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    有效
    0.37
    TIMESTAMP
    0.36
    ابات
    0.35
    无效
    0.34
    られない
    0.33
    反复
    0.33
     방정식
    0.32
     করিয়াছিল
    0.32
    有效的
    0.32
    FLICT
    0.32
    POSITIVE LOGITS
     agak
    0.54
     somewhat
    0.51
     busier
    0.51
    やや
    0.50
     rustic
    0.49
     understated
    0.48
     predomin
    0.47
     biraz
    0.47
     stod
    0.47
     onus
    0.47
    Act Density 0.221%

    No Known Activations