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

    Neuronpedia

    INDEX
    Explanations

    documented history

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     correttamente
    1.28
    ylinder
    1.19
    Categoria
    1.15
    tted
    1.11
     corretamente
    1.05
     garantiert
    0.99
    grades
    0.98
    properties
    0.96
    렀
    0.94
    generation
    0.94
    POSITIVE LOGITS
     fellowship
    1.18
    িক
    1.07
    та
    1.07
    ோ
    1.07
     phần
    1.04
    逺
    1.03
    ﺯ
    1.03
     couch
    1.02
    拏
    1.00
    ያን
    1.00
    Act Density 0.000%

    No Known Activations