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

    Neuronpedia

    INDEX
    Explanations

    divisibility and primality checks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bio
    0.40
     Typical
    0.37
     GPS
    0.36
     Biom
    0.36
     Geo
    0.35
    Bio
    0.35
     Rapid
    0.35
    ～
    0.35
     min
    0.35
    )](
    0.35
    POSITIVE LOGITS
     açısından
    0.41
     Unterschiede
    0.41
    秵
    0.40
     unterschied
    0.40
     grated
    0.40
    谀
    0.39
    单击
    0.39
    बानी
    0.39
    ábamos
    0.39
    櫛
    0.39
    Act Density 0.003%

    No Known Activations