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

    Neuronpedia

    INDEX
    Explanations

    which, który, который

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ividual
    0.75
    airement
    0.74
    iscuit
    0.71
    nent
    0.70
    steak
    0.66
    nue
    0.65
     entera
    0.65
    cap
    0.64
     saja
    0.64
    openia
    0.64
    POSITIVE LOGITS
     که
    1.14
     jotka
    1.08
     които
    1.07
     которые
    1.06
     który
    1.06
     which
    1.02
     который
    0.99
     jonka
    0.98
     who
    0.96
     które
    0.96
    Act Density 0.035%

    No Known Activations