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

    Neuronpedia

    INDEX
    Explanations

    apparently, evidently

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     misalnya
    0.52
     например
    0.46
     topologies
    0.45
     hideous
    0.45
     horrendous
    0.45
     bijvoorbeeld
    0.43
    например
    0.42
    例えば
    0.41
     असंख्य
    0.41
     siècle
    0.41
    POSITIVE LOGITS
    Apparently
    0.61
     apparently
    0.60
     evidently
    0.58
     Apparently
    0.57
     offenbar
    0.54
    apparently
    0.53
     Evidently
    0.52
     असून
    0.51
    idently
    0.46
    했으며
    0.45
    Act Density 0.086%

    No Known Activations