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

    Neuronpedia

    INDEX
    Explanations

    loyalty, loyal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    сила
    0.40
    BOR
    0.40
    riv
    0.39
    QX
    0.38
    sieh
    0.37
    Riv
    0.37
    iscale
    0.37
    rach
    0.36
    SF
    0.36
    enez
    0.35
    POSITIVE LOGITS
    alty
    1.11
     loyal
    0.87
    yal
    0.80
    alt
    0.77
    alti
    0.76
     Loyal
    0.75
    auté
    0.74
    ALT
    0.74
    alta
    0.70
    ্যাল
    0.69
    Act Density 0.002%

    No Known Activations