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

    Neuronpedia

    INDEX
    Explanations

    causing, routing, comparable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +
    0.44
    نی
    0.42
    INA
    0.41
    Toe
    0.41
     voda
    0.40
    Sov
    0.39
    Baba
    0.39
    ENDO
    0.39
    프
    0.39
    STEM
    0.39
    POSITIVE LOGITS
     comparable
    0.51
     an
    0.49
    类似于
    0.47
     similar
    0.46
     useful
    0.45
     Comparable
    0.45
     analogous
    0.45
    ণিজ্য
    0.44
    と同じ
    0.44
     campaigning
    0.43
    Act Density 0.000%

    No Known Activations