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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    JP
    -0.07
     OS
    -0.07
     이해
    -0.07
    .Highlight
    -0.07
     Tanner
    -0.07
    ائج
    -0.06
    wich
    -0.06
    	Field
    -0.06
     battled
    -0.06
     shores
    -0.06
    POSITIVE LOGITS
    ゞ
    0.07
    elmet
    0.06
    ποίηση
    0.06
     голова
    0.06
    ковой
    0.06
    inbox
    0.06
     Lux
    0.06
    गढ
    0.06
     Укра
    0.06
    ocking
    0.06
    Act Density 0.001%

    No Known Activations