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

    Neuronpedia

    INDEX
    Explanations

    time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aproxim
    -0.07
     (${
    -0.07
     BUF
    -0.07
    ْه
    -0.06
     Eduardo
    -0.06
     assassin
    -0.06
    ğı
    -0.06
     내
    -0.06
    Students
    -0.06
    para
    -0.06
    POSITIVE LOGITS
    rescia
    0.06
    ,dim
    0.06
     stripslashes
    0.06
     ответствен
    0.06
    ileges
    0.06
    Iterator
    0.06
     bum
    0.06
     ****************
    0.06
     ekip
    0.06
     Queries
    0.06
    Act Density 0.016%

    No Known Activations