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

    Neuronpedia

    INDEX
    Explanations

    code and writing instructions

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ası
    1.04
    ்துற
    0.93
    miş
    0.85
    alı
    0.85
    unst
    0.84
    ்துறை
    0.83
     końca
    0.83
    𝘳
    0.82
    лізу
    0.82
     पढ़ना
    0.82
    POSITIVE LOGITS
     Celsius
    0.91
    /$
    0.84
     Cim
    0.80
     Gré
    0.80
     Vee
    0.80
     Cervantes
    0.78
     CFC
    0.77
     réel
    0.77
     livre
    0.76
     Maduro
    0.76
    Act Density 0.000%

    No Known Activations