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

    Neuronpedia

    INDEX
    Explanations

    numerical calculations and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ，
    0.46
    、
    0.38
     রাখার
    0.38
    賂
    0.38
     nên
    0.37
     hiểm
    0.37
     সম্ভাবনা
    0.37
     sebab
    0.36
    也可
    0.36
     podendo
    0.35
    POSITIVE LOGITS
    0.43
     squats
    0.42
     wai
    0.41
     $
    0.40
    categorie
    0.40
    <h3>
    0.39
    alunos
    0.39
     largest
    0.39
    MPs
    0.39
     regarding
    0.39
    Act Density 0.000%

    No Known Activations