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

    Neuronpedia

    INDEX
    Explanations

    experience, health, safety, SQL

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    0.46
     receive
    0.45
     capabilities
    0.45
     releases
    0.44
     pesky
    0.43
    는
    0.42
    ce
    0.41
     deliverables
    0.41
    ಸೆ
    0.41
     lance
    0.40
    POSITIVE LOGITS
     फिल्मी
    0.48
     accanto
    0.47
     modernist
    0.47
     opini
    0.47
    訸
    0.45
    odoro
    0.45
    𝚄
    0.44
    oną
    0.44
    ož
    0.44
    ეც
    0.43
    Act Density 0.001%

    No Known Activations