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

    Neuronpedia

    INDEX
    Explanations

    if or although clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lambda
    0.42
    Callback
    0.41
     shipped
    0.41
     ఇచ్చిన
    0.39
    îne
    0.38
     তারিখ
    0.37
     व्हायरल
    0.37
    を務
    0.37
    ature
    0.37
     작성
    0.37
    POSITIVE LOGITS
     pokud
    0.62
     hvis
    0.52
     if
    0.52
    ถ้า
    0.51
     although
    0.49
     jeśli
    0.48
     jeżeli
    0.48
     якщо
    0.48
    если
    0.47
    如果你
    0.47
    Act Density 0.017%

    No Known Activations