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

    Neuronpedia

    INDEX
    Explanations

    gratitude and introduction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     harassing
    0.52
     harassed
    0.51
     harassment
    0.47
     제품
    0.46
     시스템
    0.45
    र्सेज
    0.45
    ס
    0.44
    YNAMIC
    0.44
    𝗲
    0.43
     बाजार
    0.43
    POSITIVE LOGITS
     honorary
    0.42
    としても
    0.41
     Appendix
    0.41
     πρώ
    0.41
    0.41
     उतनी
    0.40
    作为
    0.39
    γγ
    0.39
     aufgrund
    0.38
    μένη
    0.38
    Act Density 0.002%

    No Known Activations