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

    Neuronpedia

    INDEX
    Explanations

    if eligible

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Taxonomic
    0.99
     implementación
    0.92
     Localization
    0.89
     उपयोगकर्ताओं
    0.89
     Kontext
    0.88
     RuntimeError
    0.86
     Parsing
    0.86
     taxonomic
    0.85
     spatially
    0.84
     perturbative
    0.84
    POSITIVE LOGITS
     you
    1.27
     if
    1.23
     your
    1.19
    your
    1.11
    if
    1.09
     nếu
    1.07
    you
    1.06
    你可以
    1.06
     insurance
    1.01
     bạn
    1.00
    Act Density 0.534%

    No Known Activations