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

    Neuronpedia

    INDEX
    Explanations

    lines on faces or drawings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ’,
    0.48
    )
    0.47
    ]
    0.45
    ,
    0.43
     Orsay
    0.43
    वे
    0.43
    ,’
    0.43
    Important
    0.43
    ier
    0.42
    :,
    0.41
    POSITIVE LOGITS
    没有
    0.56
    قتص
    0.55
    ház
    0.51
    قاف
    0.51
    స్ట్రీ
    0.49
     incênd
    0.48
    ల్ప
    0.47
    連続
    0.46
    无法
    0.46
    вшись
    0.46
    Act Density 0.000%

    No Known Activations