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

    Neuronpedia

    INDEX
    Explanations

    bonds, stocks, and real estate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ad
    1.22
    of
    1.13
    ur
    1.00
    the
    0.99
    in
    0.97
    u
    0.88
    p
    0.87
    w
    0.84
    c
    0.84
    The
    0.82
    POSITIVE LOGITS
     congel
    0.79
     lágrimas
    0.78
     combattre
    0.78
     añad
    0.77
    い
    0.76
    ник
    0.75
     técnicas
    0.74
     ligera
    0.74
     océ
    0.73
     représent
    0.73
    Act Density 0.059%

    No Known Activations