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

    Neuronpedia

    INDEX
    Explanations

    questions and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Gorgeous
    0.51
     immediatamente
    0.51
     tcpHeader
    0.48
    Stabilise
    0.48
     تیز
    0.48
    Posted
    0.48
     በጣም
    0.47
     تاريخ
    0.47
    വേശ
    0.46
     yaptığı
    0.46
    POSITIVE LOGITS
     n
    0.50
    暗
    0.49
     dry
    0.49
     sub
    0.48
     dam
    0.48
     江
    0.46
     in
    0.45
     breeder
    0.45
     IC
    0.45
    江
    0.45
    Act Density 0.001%

    No Known Activations