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

    Neuronpedia

    INDEX
    Explanations

    RUST `pub` keyword

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ت
    1.15
    If
    0.98
    The
    0.97
        
    0.96
    ك
    0.96
    ین
    0.93
    न
    0.91
      
    0.89
    ن
    0.89
    Pure
    0.89
    POSITIVE LOGITS
    🙉
    1.15
    ARAJYA
    1.13
     protegido
    1.04
    😘
    1.03
    👺
    1.00
    ORES
    0.99
     prepd
    0.98
    🤥
    0.97
    👿
    0.96
    INTRESOURCE
    0.96
    Act Density 0.000%

    No Known Activations