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

    Neuronpedia

    INDEX
    Explanations

    winning dominance superiority

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     EQU
    0.47
     equal
    0.46
     ambitious
    0.46
     wę
    0.46
     uguale
    0.45
     tentar
    0.44
     inversa
    0.43
     igual
    0.42
     decentral
    0.42
     Attempt
    0.42
    POSITIVE LOGITS
     overwhelmingly
    0.78
    圧倒
    0.78
     overwhelming
    0.77
     overpowering
    0.69
     dominance
    0.66
     domination
    0.66
     dominate
    0.66
     superiority
    0.64
     victorious
    0.64
     dominates
    0.64
    Act Density 0.298%

    No Known Activations