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

    Neuronpedia

    INDEX
    Explanations

    salt and pepper

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ملاحظ
    0.46
    undant
    0.45
    Featured
    0.44
    śle
    0.43
    remarkable
    0.43
    remaining
    0.43
    uddle
    0.42
    Nelson
    0.41
    Allowed
    0.41
     못
    0.41
    POSITIVE LOGITS
     ingredientes
    0.46
     depre
    0.46
     dormitorio
    0.45
     inflación
    0.45
     eş
    0.44
    বান্ধ
    0.44
     obiettivo
    0.44
     afecta
    0.44
     eficaz
    0.43
     cặp
    0.43
    Act Density 0.001%

    No Known Activations