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

    Neuronpedia

    INDEX
    Explanations

    unique, local, complex

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    different
    0.47
     different
    0.44
    今回は
    0.44
    mba
    0.44
     Different
    0.42
     diferentes
    0.42
     diferente
    0.41
    ¿
    0.41
    Different
    0.40
    $\
    0.40
    POSITIVE LOGITS
    规范
    0.47
     маршру
    0.44
     сложные
    0.42
     लय
    0.41
     город
    0.41
     நன்மை
    0.41
    不能
    0.41
     местные
    0.40
    独特的
    0.40
     marshes
    0.40
    Act Density 0.012%

    No Known Activations