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

    Neuronpedia

    INDEX
    Explanations

    numbers and foreign text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Presidente
    0.43
    ina
    0.40
     it
    0.40
     a
    0.37
    in
    0.36
     you
    0.35
    t
    0.35
     is
    0.34
     $
    0.34
    cito
    0.34
    POSITIVE LOGITS
    ور
    0.43
    3
    0.43
    га
    0.40
    4
    0.37
    办法
    0.36
    ある
    0.36
    ون
    0.36
    データを
    0.36
    ע
    0.34
    NI
    0.34
    Act Density 1.117%

    No Known Activations