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

    Neuronpedia

    INDEX
    Explanations

    instead of alternatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    についても
    0.45
    においても
    0.42
     cũng
    0.42
     помимо
    0.42
    artifactId
    0.42
    ARMA
    0.41
    我也
    0.41
     my
    0.39
    にも
    0.39
     datasheet
    0.38
    POSITIVE LOGITS
     नये
    0.41
    instead
    0.41
     cheaper
    0.41
     Gradually
    0.40
     directa
    0.39
     instead
    0.38
    更能
    0.38
     invece
    0.37
     Instead
    0.37
     Spaniards
    0.37
    Act Density 0.019%

    No Known Activations