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

    Neuronpedia

    INDEX
    Explanations

    purpose-built dome

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.54
    z
    0.53
     et
    0.52
     רבים
    0.50
    k
    0.48
    y
    0.47
    0
    0.46
    size
    0.45
    });
    0.45
    ]):
    0.45
    POSITIVE LOGITS
     стрельца
    0.54
    ອາຫານ
    0.52
    гим
    0.49
    อาหาร
    0.49
    扑
    0.47
    ૨
    0.47
    Excel
    0.46
    ర్వాత
    0.45
    ხვევ
    0.45
    áticas
    0.45
    Act Density 0.000%

    No Known Activations