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

    Neuronpedia

    INDEX
    Explanations

    living vs non-living; offline access

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     SalesLT
    2.07
    𝑧
    2.05
    dplyr
    2.02
    ⎝
    1.90
    സ
    1.86
     улицы
    1.84
    これ
    1.83
     glances
    1.82
    GameObject
    1.81
     keluar
    1.79
    POSITIVE LOGITS
    ریشن
    1.68
     sẵn
    1.61
     own
    1.44
    上の
    1.44
     подхода
    1.43
    uración
    1.42
    ⁦
    1.42
    েই
    1.41
     própria
    1.40
    ympt
    1.40
    Act Density 0.007%

    No Known Activations