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

    Neuronpedia

    INDEX
    Explanations

    Math expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     فکر
    -0.08
    =https
    -0.08
    =[],
    -0.08
    [ind
    -0.07
    =os
    -0.07
    obod
    -0.07
     VAN
    -0.07
     sit
    -0.07
     유
    -0.07
    occo
    -0.07
    POSITIVE LOGITS
    antos
    0.09
     sealed
    0.08
     sealing
    0.07
    ുറ
    0.07
     klimaat
    0.07
     paprika
    0.07
     cui
    0.07
    ുര
    0.07
    -sided
    0.07
     gema
    0.07
    Act Density 0.032%

    No Known Activations