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

    Neuronpedia

    INDEX
    Explanations

    and so on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     మాత్రం
    0.50
     firstly
    0.42
     ligeramente
    0.40
     slightly
    0.40
     instead
    0.39
    0.39
     beide
    0.39
     somewhat
    0.38
     légèrement
    0.38
    HAHA
    0.38
    POSITIVE LOGITS
     lainnya
    0.78
     기타
    0.68
     подобных
    0.64
    還有
    0.61
    その他
    0.60
     असंख्य
    0.59
     подобные
    0.59
    といった
    0.58
     sebagainya
    0.58
    whatever
    0.57
    Act Density 0.040%

    No Known Activations