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

    Neuronpedia

    INDEX
    Explanations

    * important phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ר
    0.69
    ر
    0.66
     Painter
    0.66
    na
    0.63
    лля
    0.63
    െടുത്ത
    0.63
     større
    0.63
     \
    0.63
     그다음에
    0.63
    ऊदी
    0.63
    POSITIVE LOGITS
    年会
    0.81
     अन्तर
    0.80
     دستاویز
    0.79
    UIControl
    0.77
     sacrificing
    0.77
     financiera
    0.76
    szak
    0.76
    ocument
    0.76
     replicating
    0.76
    ogether
    0.75
    Act Density 0.000%

    No Known Activations