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

    Neuronpedia

    INDEX
    Explanations

    NTU comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     offsetX
    0.31
     ιστο
    0.31
    历史
    0.30
     পুরোনো
    0.29
    维护
    0.29
    的历史
    0.29
    बर्ट
    0.28
     исторических
    0.28
     ঐতিহাসিক
    0.28
     套
    0.28
    POSITIVE LOGITS
     geophysical
    0.35
     શ
    0.31
     शारीरिक
    0.29
     Militar
    0.29
     izango
    0.28
     physico
    0.28
     thermoplastic
    0.28
     slimming
    0.28
     dihydro
    0.27
     physic
    0.27
    Act Density 0.254%

    No Known Activations