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

    Neuronpedia

    INDEX
    Explanations

    seeks/interactions

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     court
    0.54
    Court
    0.50
     Court
    0.46
    court
    0.44
     COURT
    0.38
     カラ
    0.37
    ื่น
    0.37
    বন্দ
    0.36
    퀸
    0.35
    ರಿನ
    0.35
    POSITIVE LOGITS
     courts
    1.93
     Courts
    1.85
    courts
    1.67
     wo
    1.46
     Wo
    1.14
    Wo
    1.13
    wo
    1.09
    Cour
    1.09
     WO
    1.05
    WO
    0.94
    Act Density 0.026%

    No Known Activations