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

    Neuronpedia

    INDEX
    Explanations

    Quotations/Excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    writers
    -0.06
     shoe
    -0.06
    áno
    -0.06
    rale
    -0.06
     apologies
    -0.06
    .annotation
    -0.06
     Mex
    -0.06
    Reg
    -0.06
     mantra
    -0.06
     берез
    -0.06
    POSITIVE LOGITS
    	   ↵
    0.07
     lk
    0.07
     preco
    0.06
     Вол
    0.06
    entanyl
    0.06
    ニﾆ
    0.06
    еля
    0.06
    ollipop
    0.06
     вищ
    0.06
    ،↵
    0.06
    Act Density 0.325%

    No Known Activations