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

    Neuronpedia

    INDEX
    Explanations

    Native Rendering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    мія
    0.52
    alogy
    0.47
    iin
    0.47
    คุณ
    0.46
    thers
    0.46
    threatening
    0.45
    Scaled
    0.45
    alur
    0.44
     وید
    0.44
    㖅
    0.44
    POSITIVE LOGITS
     inventories
    0.50
     dung
    0.50
     cultivos
    0.46
    𝘽
    0.45
     especies
    0.44
     surpluses
    0.44
    य
    0.44
     primeiros
    0.43
     poblaciones
    0.43
    ایط
    0.43
    Act Density 0.004%

    No Known Activations