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

    Neuronpedia

    INDEX
    Explanations

    geopolitical advantages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AWAY
    0.43
     Hij
    0.43
     Coc
    0.42
     Hib
    0.42
     hij
    0.41
     Kub
    0.41
     Fairy
    0.41
     ângulo
    0.40
     Cat
    0.40
     Ai
    0.40
    POSITIVE LOGITS
     toxicants
    0.47
    boomerang
    0.43
    abo
    0.43
     sediments
    0.43
     sulfides
    0.43
    ureau
    0.42
    cumsum
    0.41
    cumulative
    0.41
    ohnt
    0.40
    geordnet
    0.40
    Act Density 0.000%

    No Known Activations