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

    Neuronpedia

    INDEX
    Explanations

    professional titles and names

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nick
    0.59
     मता
    0.58
    𝑀
    0.54
    ẩy
    0.53
     Nich
    0.53
    ծ
    0.52
    琳
    0.52
    缅
    0.52
     Dev
    0.52
    ],$
    0.52
    POSITIVE LOGITS
    gruppen
    0.59
     Healthcare
    0.54
    コマンド
    0.54
    什麼
    0.54
     vielleicht
    0.54
     utili
    0.53
     utile
    0.52
     तारी
    0.52
     troll
    0.52
    ocortic
    0.52
    Act Density 0.001%

    No Known Activations