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

    Neuronpedia

    INDEX
    Explanations

    it's a shame they

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tradition
    1.16
     Adventure
    1.07
     INE
    1.04
     leave
    1.02
     испан
    0.99
     Nevada
    0.99
     Emerg
    0.98
     Traditions
    0.97
     Latino
    0.96
    хь
    0.96
    POSITIVE LOGITS
    eal
    1.16
    hlas
    1.07
    adika
    1.07
    )$:
    1.02
    edos
    1.02
    ...+
    1.00
     pretože
    0.99
    ycji
    0.99
    góc
    0.98
    none
    0.97
    Act Density 0.001%

    No Known Activations