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

    Neuronpedia

    INDEX
    Explanations

    explanation or clarification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     getMax
    0.51
    犒
    0.50
     desmont
    0.45
     compartir
    0.43
    الك
    0.42
     getCurrent
    0.42
     đựng
    0.41
    ب
    0.41
     indispensable
    0.40
    ขั้นตอน
    0.40
    POSITIVE LOGITS
    _)
    0.55
    )
    0.54
    ）
    0.48
    reg
    0.48
    ！）
    0.48
    red
    0.47
    sor
    0.46
     Coulter
    0.46
    蝓
    0.46
    renner
    0.45
    Act Density 0.013%

    No Known Activations