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

    Neuronpedia

    INDEX
    Explanations

    with followed by specific technical/descriptive words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     другими
    0.41
    সুতরাং
    0.40
    worldly
    0.38
     satış
    0.38
     других
    0.38
     önemlidir
    0.38
     আসিয়
    0.37
     కేసులు
    0.37
     더욱
    0.37
     nomencl
    0.36
    POSITIVE LOGITS
     a
    0.58
     the
    0.49
     N
    0.48
     T
    0.45
     D
    0.45
     K
    0.45
     with
    0.43
     any
    0.43
     A
    0.42
     either
    0.42
    Act Density 0.074%

    No Known Activations