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

    Neuronpedia

    INDEX
    Explanations

    question and answer format

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    درا
    0.43
    你了
    0.41
     analisar
    0.40
     analyse
    0.40
     girişim
    0.40
     implications
    0.39
     использоваться
    0.39
    ادر
    0.39
     visualisation
    0.38
     odnosu
    0.38
    POSITIVE LOGITS
    uese
    0.40
    odo
    0.39
    bol
    0.39
    ikian
    0.39
    ib
    0.38
    olo
    0.37
     ዋ
    0.37
    terminate
    0.37
    Number
    0.37
    hombre
    0.37
    Act Density 0.011%

    No Known Activations