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

    Neuronpedia

    INDEX
    Explanations

    LaTeX environments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     সোভ
    0.42
     право
    0.41
     Bonif
    0.41
     町
    0.41
     সম্মত
    0.40
     Shots
    0.40
    டும்ப
    0.39
     Puoi
    0.39
     методи
    0.38
    義務
    0.38
    POSITIVE LOGITS
    while
    0.54
    centering
    0.46
    Acer
    0.43
    Nav
    0.43
    rid
    0.42
    logging
    0.41
    Bal
    0.41
    try
    0.41
    return
    0.39
    Sure
    0.39
    Act Density 0.001%

    No Known Activations