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

    Neuronpedia

    INDEX
    Explanations

    individual

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    the
    1.81
    to
    1.51
    s
    1.46
    k
    1.45
    ts
    1.38
    t
    1.36
    it
    1.30
    b
    1.22
    ओं
    1.11
    y
    1.10
    POSITIVE LOGITS
    ,
    1.45
    প্রায়
    1.13
    ла
    1.12
     beiden
    1.06
     projetos
    1.05
    ć
    1.03
    يه
    1.02
     sechs
    1.02
    E
    1.01
     criticize
    0.98
    Act Density 0.002%

    No Known Activations