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

    Neuronpedia

    INDEX
    Explanations

    com.example

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ipso
    0.88
    ಾರ್ಥ
    0.81
    ekš
    0.77
    roph
    0.77
    㳊
    0.76
     যথেষ্ট
    0.76
     pyroph
    0.75
    ::_
    0.74
     estánd
    0.74
    intensité
    0.73
    POSITIVE LOGITS
     company
    1.13
    atgu
    0.85
     companies
    0.83
     inquiry
    0.83
     뿐
    0.80
     few
    0.80
    company
    0.79
     capital
    0.79
    entreprise
    0.79
     คอม
    0.78
    Act Density 0.001%

    No Known Activations