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

    Neuronpedia

    INDEX
    Explanations

    wikipedia talk and edits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kaleidos
    0.46
     város
    0.42
     لاز
    0.42
     zonas
    0.40
     céu
    0.40
     proiect
    0.39
     chaleur
    0.39
     '':
    0.39
     showrooms
    0.39
     Combine
    0.38
    POSITIVE LOGITS
    𒁳
    0.53
    talk
    0.46
    这个人
    0.44
    留言
    0.44
     talked
    0.43
     talk
    0.43
    Talk
    0.42
     talks
    0.42
    编辑
    0.41
     edits
    0.39
    Act Density 0.002%

    No Known Activations