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

    Neuronpedia

    INDEX
    Explanations

    power app input field description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BREED
    0.43
     модуля
    0.42
    λοι
    0.41
     corde
    0.38
     길
    0.37
    ᠰ
    0.36
    льский
    0.36
    Jill
    0.35
     Евгений
    0.35
    年后
    0.35
    POSITIVE LOGITS
    rer
    0.37
    బు
    0.36
    cd
    0.36
     inmig
    0.35
     product
    0.35
     Description
    0.34
    商品は
    0.34
     description
    0.34
    isc
    0.34
    arr
    0.34
    Act Density 0.004%

    No Known Activations