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

    Neuronpedia

    INDEX
    Explanations

    non-English text

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Civic
    1.01
    Civ
    0.98
     civic
    0.95
    civ
    0.91
     Civ
    0.89
     CIV
    0.86
     CR
    0.84
     Accord
    0.84
     civ
    0.80
    Accord
    0.78
    POSITIVE LOGITS
    ሩ
    0.36
    隆
    0.36
     Донец
    0.35
    ریہ
    0.35
    ഫ
    0.35
    Artist
    0.34
     Sach
    0.34
    قل
    0.33
     व्यास
    0.33
    Ble
    0.33
    Act Density 0.003%

    No Known Activations