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

    Neuronpedia

    INDEX
    Explanations

    specifically instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     विषय
    0.42
    原因
    0.42
    原因是
    0.40
     最後
    0.39
    پيديا
    0.38
     विविध
    0.38
     причинам
    0.38
    にとっては
    0.38
    راز
    0.37
     શોધ
    0.37
    POSITIVE LOGITS
    ignment
    0.39
     Stan
    0.39
     yatırım
    0.38
     Upt
    0.37
     iconic
    0.36
    ians
    0.36
    ț
    0.35
    unque
    0.35
     intram
    0.35
     Wildcats
    0.35
    Act Density 0.001%

    No Known Activations