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

    Neuronpedia

    INDEX
    Explanations

    walking distance or easy reach

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    1.48
     thiab
    1.43
    et
    1.24
    se
    1.22
    tter
    1.17
    sst
    1.14
    c
    1.14
    #'
    1.13
    bě
    1.13
    vection
    1.12
    POSITIVE LOGITS
     Ambedkar
    1.08
    𝖐
    1.08
    ล์
    1.05
     aufgrund
    1.05
     gleich
    1.02
    ἆ
    1.02
    ने
    1.01
    众
    1.00
    การ
    0.99
     lacus
    0.98
    Act Density 0.001%

    No Known Activations