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

    Neuronpedia

    INDEX
    Explanations

    explaining, describing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     employ
    0.45
     employed
    0.43
     неве
    0.41
     vor
    0.39
    <h3>
    0.38
    vor
    0.38
     Rural
    0.38
     লিপিবদ্ধ
    0.38
     wal
    0.37
     Labrador
    0.37
    POSITIVE LOGITS
    mentation
    0.45
     rectum
    0.41
    ⌵
    0.40
     মর্ম
    0.40
     Disrupt
    0.40
    แจ
    0.40
    痛
    0.39
    гия
    0.38
    mented
    0.38
    дко
    0.38
    Act Density 0.001%

    No Known Activations