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

    Neuronpedia

    INDEX
    Explanations

    already completed actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ỳnh
    0.38
     unterschiedlich
    0.38
    :\\
    0.38
    [![
    0.36
     पो
    0.36
    简介
    0.35
    <start_of_image>
    0.35
    }\\
    0.34
     CXCR
    0.34
     পর্যায়ের
    0.34
    POSITIVE LOGITS
    that
    0.51
    หน้าที่
    0.44
     نريد
    0.42
     that
    0.42
     आहे
    0.40
     источник
    0.40
     যেহেতু
    0.38
    願意
    0.38
    yin
    0.37
     Want
    0.37
    Act Density 0.001%

    No Known Activations