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

    Neuronpedia

    INDEX
    Explanations

    ("respectively

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Может
    0.95
    िटर
    0.95
    珀
    0.93
     Первый
    0.90
     Более
    0.89
    ewnętr
    0.89
     empiezan
    0.89
     extracción
    0.87
    стый
    0.86
     Cualquier
    0.86
    POSITIVE LOGITS
     tast
    0.73
    enumi
    0.68
    ু
    0.67
    DEM
    0.66
    мога
    0.65
     retrieves
    0.65
    MAK
    0.64
     prompt
    0.64
     (
    0.63
     telephones
    0.63
    Act Density 0.003%

    No Known Activations