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

    Neuronpedia

    INDEX
    Explanations

    step

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ????
    -0.07
     nop
    -0.07
     корот
    -0.06
     complications
    -0.06
    _Draw
    -0.06
    ,error
    -0.06
            
    -0.06
    >S
    -0.06
     ري
    -0.06
     หร
    -0.06
    POSITIVE LOGITS
    ovna
    0.07
     indis
    0.07
    paginate
    0.06
    Tab
    0.06
     Nevada
    0.06
     Libraries
    0.06
     XIII
    0.06
    xford
    0.06
    تر
    0.06
    ư
    0.06
    Act Density 0.003%

    No Known Activations