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

    Neuronpedia

    INDEX
    Explanations

    what is required

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ช
    0.51
    iktok
    0.43
    ಕ್ಕು
    0.43
    ເກ
    0.43
    ática
    0.42
    0.42
    ק
    0.42
    파
    0.41
    상
    0.41
    ह
    0.41
    POSITIVE LOGITS
     വ്യാ
    0.43
     jsem
    0.42
    veren
    0.42
     മരണ
    0.41
     corso
    0.40
     `
    0.40
     graag
    0.40
     الأرض
    0.40
     założ
    0.40
    vez
    0.39
    Act Density 0.001%

    No Known Activations