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

    Neuronpedia

    INDEX
    Explanations

    automation and product formulation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    สามารถ
    0.46
    椙
    0.46
    慜
    0.46
    AL
    0.45
    อาจ
    0.44
    浴
    0.44
    桫
    0.44
    Unis
    0.44
    ภาษ
    0.44
    瘍
    0.44
    POSITIVE LOGITS
     bc
    0.48
     aristocratic
    0.43
     fill
    0.43
     Craft
    0.43
     campeón
    0.43
     đổi
    0.43
     Britons
    0.43
     countertops
    0.42
     equations
    0.42
     histó
    0.42
    Act Density 0.001%

    No Known Activations