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

    Neuronpedia

    INDEX
    Explanations

    questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     här
    -0.07
     synchronization
    -0.06
    ondere
    -0.06
    _slot
    -0.06
    rant
    -0.06
     mc
    -0.06
     detay
    -0.06
    -ton
    -0.06
    ;');↵
    -0.06
    scheduler
    -0.06
    POSITIVE LOGITS
     relocated
    0.06
    ῆς
    0.06
     PANEL
    0.06
    we
    0.06
     جنگ
    0.06
    міністра
    0.06
     사람이
    0.06
     پاسخ
    0.06
    англ
    0.06
     matrimon
    0.06
    Act Density 0.021%

    No Known Activations