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

    Neuronpedia

    INDEX
    Explanations

    code and calculation elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    elten
    0.57
     ፍ
    0.55
     Europäischen
    0.52
     Гульнявыя
    0.52
    ро
    0.50
     ко
    0.49
     મળી
    0.49
     කා
    0.48
     предназначен
    0.48
    gün
    0.48
    POSITIVE LOGITS
    一
    0.58
    אם
    0.53
    _
    0.53
     altercation
    0.49
    一本
    0.49
    য
    0.48
     exec
    0.48
     halides
    0.47
    //
    0.47
    य
    0.46
    Act Density 0.000%

    No Known Activations