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

    Neuronpedia

    INDEX
    Explanations

    occasions and occasional uses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     a
    1.17
    માં
    1.06
    ],
    1.05
    า
    0.99
    มีความ
    0.95
    し
    0.95
    ia
    0.91
     simul
    0.91
     manter
    0.90
    د
    0.89
    POSITIVE LOGITS
    m
    1.89
    is
    1.71
    l
    1.47
    p
    1.20
    n
    1.19
    th
    1.07
    miles
    1.07
    muy
    1.06
    ли
    1.05
    li
    1.05
    Act Density 0.123%

    No Known Activations