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

    Neuronpedia

    INDEX
    Explanations

    learning and language

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    제
    0.59
    가
    0.59
    가를
    0.50
    가의
    0.50
    加
    0.49
    제로
    0.47
    가가
    0.40
    ms
    0.40
    제의
    0.39
    khan
    0.38
    POSITIVE LOGITS
    monary
    0.37
    ваем
    0.37
    ުން
    0.36
     बूंद
    0.35
    待ち
    0.34
    eqref
    0.34
    ipelago
    0.34
    ुत
    0.33
     tính
    0.32
    затор
    0.32
    Act Density 0.000%

    No Known Activations