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

    Neuronpedia

    INDEX
    Explanations

    risk, cost, effort, strategy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     उतने
    0.36
     antr
    0.35
     excessively
    0.34
    สรร
    0.34
     concluding
    0.34
     topl
    0.34
    хой
    0.34
     est
    0.33
     anu
    0.33
     erf
    0.33
    POSITIVE LOGITS
    বিশিষ্ট
    0.67
     वाली
    0.61
     वाले
    0.54
    മുള്ള
    0.52
    விலான
    0.51
    ുള്ള
    0.51
     অধিকারী
    0.50
     கொண்ட
    0.47
    முடைய
    0.46
     affair
    0.45
    Act Density 0.082%

    No Known Activations