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

    Neuronpedia

    INDEX
    Explanations

    disintegration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tract
    0.44
     gild
    0.38
     frug
    0.38
    舩
    0.38
     Roundtable
    0.38
     dividend
    0.37
     naw
    0.37
     дерево
    0.36
     shabd
    0.36
     broader
    0.36
    POSITIVE LOGITS
     मरी
    0.41
    eres
    0.40
     HTTPException
    0.39
    อน
    0.39
    விர
    0.39
    блица
    0.38
    पती
    0.38
    ingar
    0.38
    発表
    0.37
     abnormalities
    0.37
    Act Density 0.011%

    No Known Activations