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

    Neuronpedia

    INDEX
    Explanations

    anti-lock braking system

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    í
    0.68
    fulfill
    0.57
    f
    0.55
    zés
    0.55
    !\
    0.53
    ectomy
    0.53
     avi
    0.52
    anges
    0.50
     enhance
    0.50
     Bye
    0.50
    POSITIVE LOGITS
    ри
    0.59
    บ
    0.56
    তিকর
    0.55
    ล
    0.55
    뷸
    0.54
    ни
    0.54
     доро
    0.54
     denaro
    0.54
     нього
    0.53
     europ
    0.53
    Act Density 0.003%

    No Known Activations