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

    Neuronpedia

    INDEX
    Explanations

    kotlin code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    让我
    0.44
    让你
    0.43
     શકે
    0.43
     let
    0.43
     ड्रेस
    0.39
    膘
    0.39
    CRR
    0.39
     चलो
    0.39
    लिप
    0.38
     دونك
    0.38
    POSITIVE LOGITS
     val
    1.00
    val
    0.99
    fun
    0.88
     fun
    0.80
     Val
    0.71
    late
    0.66
     Fun
    0.64
    VAL
    0.62
    Val
    0.61
     late
    0.59
    Act Density 0.007%

    No Known Activations