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

    Neuronpedia

    INDEX
    Explanations

    nine different

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     പറയ
    0.54
     næ
    0.53
     yüz
    0.52
     wajah
    0.50
     misalnya
    0.50
    戛
    0.50
     Mene
    0.50
     Öğ
    0.49
     जैसी
    0.49
     Им
    0.48
    POSITIVE LOGITS
    der
    0.54
    du
    0.50
    court
    0.49
    zinger
    0.47
    liner
    0.46
     trocar
    0.46
    indo
    0.46
    bolt
    0.46
    s
    0.45
    ăng
    0.45
    Act Density 0.000%

    No Known Activations