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

    Neuronpedia

    INDEX
    Explanations

    experiment with different

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    kita
    0.54
     accomplishments
    0.43
    check
    0.41
    screen
    0.41
    adati
    0.40
    tour
    0.39
    challenge
    0.39
    executed
    0.38
    analysis
    0.38
    ack
    0.38
    POSITIVE LOGITS
     different
    1.02
     diferentes
    0.92
    不同的
    0.90
     différentes
    0.86
     verschillende
    0.84
     różnych
    0.83
     разные
    0.82
     Different
    0.81
     forskellige
    0.81
     diferente
    0.80
    Act Density 0.010%

    No Known Activations