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

    Neuronpedia

    INDEX
    Explanations

    python code examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ويمكن
    0.42
    フィス
    0.40
     Enh
    0.38
    yk
    0.38
    ulagway
    0.38
    相信
    0.37
     δημιουργ
    0.36
     Cres
    0.36
     उनकी
    0.35
     они
    0.35
    POSITIVE LOGITS
     pigs
    0.46
     clothe
    0.46
     police
    0.44
     thr
    0.43
     cloth
    0.43
     vict
    0.43
     quarrels
    0.43
     paper
    0.43
     govern
    0.43
     calves
    0.43
    Act Density 0.008%

    No Known Activations