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

    Neuronpedia

    INDEX
    Explanations

    error handling code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MAKE
    0.72
    FARE
    0.61
    USTR
    0.57
     پک
    0.57
    CAPTURE
    0.56
     AND
    0.55
    采样
    0.55
    ულ
    0.55
    HELP
    0.55
    WATER
    0.54
    POSITIVE LOGITS
    ating
    0.71
    ra
    0.66
    on
    0.66
     Erwachsene
    0.63
     nakon
    0.63
    จาก
    0.61
    da
    0.59
     මෙම
    0.59
    de
    0.58
    te
    0.56
    Act Density 0.149%

    No Known Activations