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

    Neuronpedia

    INDEX
    Explanations

    code file paths and data handling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sthe
    1.64
    1
    1.51
    </strong>
    1.38
    c
    1.35
    ik
    1.29
    t
    1.23
    gestion
    1.21
     stroll
    1.20
    2
    1.20
    ان
    1.19
    POSITIVE LOGITS
     níveis
    1.35
    ều
    1.33
     ľud
    1.30
    тся
    1.29
     líqu
    1.28
    というか
    1.26
    𝔪
    1.26
     қа
    1.23
    เป็น
    1.21
     zwią
    1.21
    Act Density 0.215%

    No Known Activations