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

    Neuronpedia

    INDEX
    Explanations

    numbers of people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ння
    0.48
    るので
    0.47
    ถ้า
    0.46
     میلیون
    0.45
     milioni
    0.44
     EBITDA
    0.44
     tathapi
    0.44
     تعالی
    0.43
    પતિ
    0.43
    ρα
    0.43
    POSITIVE LOGITS
    D
    0.63
    V
    0.60
    L
    0.59
    o
    0.57
    W
    0.56
    T
    0.54
    E
    0.53
    л
    0.53
    Roles
    0.50
    S
    0.50
    Act Density 0.001%

    No Known Activations