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

    Neuronpedia

    INDEX
    Explanations

    €, Danube, tech, fast, sleep, Power

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ၀၀
    0.93
     sulfuric
    0.80
    hah
    0.80
    ginas
    0.76
     Smyth
    0.76
     Sons
    0.75
     Amerikan
    0.75
    0.75
     derechos
    0.75
     ör
    0.75
    POSITIVE LOGITS
    精心
    0.96
    ਕ
    0.90
    ം
    0.89
    วันนี้
    0.89
    ನಲ್ಲಿ
    0.89
    Wie
    0.84
    料
    0.84
    та
    0.83
     început
    0.82
    ية
    0.81
    Act Density 0.000%

    No Known Activations