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

    Neuronpedia

    INDEX
    Explanations

    early social structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    okkaido
    0.70
     mjesto
    0.69
     contractual
    0.67
     praying
    0.64
     귀
    0.64
     bowing
    0.64
     sweetness
    0.64
     wetting
    0.64
     ಸ್ವಾ
    0.64
    play
    0.63
    POSITIVE LOGITS
     They
    0.79
    цо
    0.77
     THEY
    0.76
     personaje
    0.73
    ണിത്
    0.73
    They
    0.73
    جم
    0.73
     они
    0.71
    தெ
    0.70
     questo
    0.70
    Act Density 0.000%

    No Known Activations