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

    Neuronpedia

    INDEX
    Explanations

    relative pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     вашу
    0.36
    DWORD
    0.36
    BOLD
    0.35
    されている
    0.34
    尤其是
    0.34
     olnud
    0.34
     була
    0.33
    發生
    0.33
    ായത്
    0.33
    Walmart
    0.33
    POSITIVE LOGITS
     which
    0.82
     who
    0.71
     который
    0.67
     yang
    0.61
     който
    0.61
     koji
    0.61
     Which
    0.60
     которая
    0.59
     الذي
    0.59
     whose
    0.58
    Act Density 0.003%

    No Known Activations