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

    Neuronpedia

    INDEX
    Explanations

    other languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nerdy
    0.52
     unapolog
    0.50
     craziness
    0.50
     greats
    0.50
     bernama
    0.49
     sneaky
    0.49
     shenanigans
    0.48
     mücade
    0.47
     wacky
    0.47
     punya
    0.47
    POSITIVE LOGITS
     例文帳に追加
    0.60
    también
    0.50
    例文帳に追加
    0.49
     অন্যান্য
    0.47
    ō
    0.47
     također
    0.46
     других
    0.46
     ಇತರ
    0.46
    ī
    0.45
    again
    0.45
    Act Density 0.003%

    No Known Activations