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

    Neuronpedia

    INDEX
    Explanations

    know how

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     เงี้ย
    0.50
     المقص
    0.41
     trusts
    0.40
    体力
    0.39
    وث
    0.39
    цима
    0.39
    酞
    0.39
    ческую
    0.37
    цю
    0.37
    ന്ത്യ
    0.36
    POSITIVE LOGITS
     adaptés
    0.46
    blog
    0.45
    node
    0.45
     yurt
    0.41
     blog
    0.41
     મને
    0.41
    python
    0.40
    intel
    0.40
     Như
    0.40
     input
    0.39
    Act Density 0.137%

    No Known Activations