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

    Neuronpedia

    INDEX
    Explanations

    Simple tasks and calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    先輩
    0.53
    ༸
    0.52
    خستان
    0.52
     вересня
    0.51
    Ⴀ
    0.51
    രംഭ
    0.50
    ジネス
    0.50
    جیب
    0.49
     ხელისუფ
    0.48
    wString
    0.48
    POSITIVE LOGITS
    s
    0.69
    0.65
    :
    0.64
    '
    0.63
    </h2>
    0.57
    -
    0.57
     Wach
    0.56
     Eric
    0.53
     '
    0.51
     Enter
    0.50
    Act Density 0.011%

    No Known Activations