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

    Neuronpedia

    INDEX
    Explanations

    latex document structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    R
    0.99
    D
    0.97
    G
    0.91
    P
    0.86
    N
    0.85
    M
    0.84
    S
    0.79
    B
    0.79
    T
    0.79
    V
    0.78
    POSITIVE LOGITS
    вите
    0.63
    ا
    0.59
    aniye
    0.57
     descuentos
    0.54
     ciudadanos
    0.54
    них
    0.54
     नाकाम
    0.54
     eCommerce
    0.52
    ా
    0.52
    iót
    0.52
    Act Density 0.001%

    No Known Activations