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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tection
    -0.07
    iti
    -0.07
     getOrder
    -0.07
     TSA
    -0.07
    (epoch
    -0.07
     protection
    -0.07
    Coverage
    -0.06
     різ
    -0.06
    STAR
    -0.06
    ujícím
    -0.06
    POSITIVE LOGITS
    (Sender
    0.07
     disput
    0.06
     personal
    0.06
    (SDL
    0.06
    циональ
    0.06
    =current
    0.06
    servers
    0.06
    estli
    0.06
     ک
    0.06
    "',
    0.06
    Act Density 0.052%

    No Known Activations