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

    Neuronpedia

    INDEX
    Explanations

    orders and arrangements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    FormField
    0.41
    ĩnh
    0.39
     형성
    0.39
    RefIn
    0.38
    Whatever
    0.38
     ឬ
    0.38
     ಪ್ರಾರಂಭ
    0.37
    ystick
    0.37
     সুমন
    0.37
    เริ่มต้น
    0.36
    POSITIVE LOGITS
     fan
    0.46
    扇
    0.43
     ORDERS
    0.41
     order
    0.41
    management
    0.40
     organising
    0.39
     ordering
    0.39
     arranging
    0.39
     Fan
    0.39
     etc
    0.38
    Act Density 0.001%

    No Known Activations