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

    Neuronpedia

    INDEX
    Explanations

    AI and engineering applications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    叓
    0.51
     Estimation
    0.50
    نوات
    0.46
     Jetzt
    0.44
     Arzneim
    0.44
     Schreiben
    0.44
    䇝
    0.44
     Scholars
    0.43
     Netzwerk
    0.43
     Medizin
    0.42
    POSITIVE LOGITS
     retrofit
    0.46
     compatible
    0.45
    在庫
    0.44
     drivetrain
    0.43
     caliper
    0.43
     கிட்டத்தட்ட
    0.42
     inbuilt
    0.42
     flange
    0.41
    兼容
    0.41
     upgrade
    0.40
    Act Density 0.013%

    No Known Activations