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

    Neuronpedia

    INDEX
    Explanations

    list formatting and placeholders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    饮食
    0.49
    匏
    0.44
    િસ
    0.44
    ாலத்தில்
    0.43
    ాల
    0.42
    ق
    0.42
    pectral
    0.42
    ersch
    0.42
    লিক
    0.41
    ુલ
    0.41
    POSITIVE LOGITS
    ใหม่
    0.50
     tume
    0.47
    ベーション
    0.45
     pesa
    0.44
    }_
    0.44
     ajud
    0.43
     หนึ่ง
    0.43
     I
    0.43
     conect
    0.43
     कब्
    0.43
    Act Density 0.000%

    No Known Activations