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

    Neuronpedia

    INDEX
    Explanations

    oath and swear

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     සැල
    0.46
     Hawk
    0.45
     hawk
    0.44
    hawk
    0.43
    ap
    0.43
    z
    0.43
    l
    0.42
     রম
    0.42
     hawks
    0.41
    屋さん
    0.41
    POSITIVE LOGITS
     oath
    1.42
     swearing
    1.34
     oaths
    1.28
     swear
    1.24
     swears
    1.23
     Oath
    1.21
     swore
    1.20
     शपथ
    1.15
     sworn
    1.14
     শপথ
    1.06
    Act Density 0.024%

    No Known Activations