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

    Neuronpedia

    INDEX
    Explanations

    feeling warm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     אחרי
    0.54
    ’
    0.54
     shoving
    0.53
     Internation
    0.52
     χ
    0.52
    τής
    0.51
     συμπ
    0.51
    that
    0.50
     yow
    0.50
    iction
    0.49
    POSITIVE LOGITS
    ح
    0.61
    ها
    0.57
    ين
    0.56
    人
    0.55
     del
    0.54
     beim
    0.54
    vidas
    0.54
    ！
    0.53
    ้าว
    0.52
    ే
    0.52
    Act Density 0.010%

    No Known Activations